Daily Papers

AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existing benchmarks mainly target financial data extraction, a narrow slice that current models have largely saturated, while reference-based metrics and generic LLM-as-a-judge scoring fall short on the open-ended, long-form answers that real analyst queries demand. We introduce FrontierFinance, a fully open benchmark of 220 expert-crafted queries and 11,543 source-attributed rubrics spanning six crucial use cases across the full investor workflow. FrontierFinance is both broader and harder than existing public finance benchmarks. Evaluating frontier models and agent systems under a common harness restricted to publicly available data, we find that the tool harness, not the model alone, strongly shapes quality and efficiency; that Samaya's in-house system leads at 56.0%, ahead of the strongest frontier model (Claude Fable 5, 49.2%) at roughly 2.2x lower cost; and that the best open-weight model (Kimi K3, 46.4%) nearly matches the best proprietary model at 4.5x lower cost. Screening & Discovery and Sector, Industry & Macro remain the hardest use cases across all systems, where even the best systems reach only 33% and 39%. We make the dataset and grading code publicly available.

Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools. Yet research has largely passed over this medium: prior systems design bespoke memory representations and study retrieval over them, leaving the default's two working assumptions untested: that an agent can keep a growing store organized as memories accumulate, conflict, and go stale, and that this organization pays. We present the first systematic exploration of filesystem-based memory for LLM agents. We formalize the setting as three roles around one memory filesystem: a management agent integrates and organizes incoming content, a search agent answers queries with cited sources, and an execution agent supplies task trajectories that are distilled into skills, unifying declarative memory and skills in a single store. Across long-conversation benchmarks and embodied tasks, we vary memory shape (agent-organized hierarchy, verbatim dump, chunk retrieval), stream scale, tool harness (sandboxed shell, memory-tool-style functions, varied search tooling), and the strengths of the management and search agents, tracking answer quality, cost, and store health as memory grows. What organization reliably buys is search economy: organized stores roughly halve retrieval cost where material is large. Today's agents, however, fall short of the default's promise: in our growth study, organization erodes for all but the strongest management agent, and no agent we measure converts organization itself into better answers. And the model is not the only lever over a store's shape: changing the tool set alone reshapes the store as strongly as swapping the model. The study turns the filesystem default from an assumption into a design space for agent memory.

Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visual context. Two bottlenecks limit current systems. First, existing tool-use harnesses treat images returned by search, browsing, or transformation as transient outputs, so intermediate visual evidence cannot be re-consumed by later tools. Second, training data is usually built by fixed curation recipes that cannot track the target agent's evolving capability. To address these challenges, we first introduce a visual-native agent harness centered on an image bank reference protocol, which registers every tool-returned image as an addressable reference and makes intermediate visual evidence reusable by later tools. On top of this harness, On-policy Data Evolution (ODE) runs a closed-loop data generator that refines itself across rounds from rollouts of the policy being trained. This per-round refinement makes each round's data target what the current policy still needs to learn. The same framework supports both diverse supervised fine-tuning data and policy-aware reinforcement learning data curation, covering the full training lifecycle of the target agent. Across 8 multimodal deep search benchmarks, ODE improves the Qwen3-VL-8B agent from 24.9% to 39.0% on average, surpassing Gemini-2.5 Pro in standard agent-workflow setting (37.9%). At 30B, ODE raises the average score from 30.6% to 41.5%. Further analyses validate the effectiveness of image-bank reuse, especially on complex tasks requiring iterative visual refinement, while rollout-feedback evolution yields more grounded SFT traces and better policy-matched RL tasks than static synthesis.

Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final output. We introduce SearchOS, a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state. First, we formulate open-domain information seeking as relational schema completion with grounded citations, where agents discover entities, populate attributes across linked tables, and anchor each value to source evidence. Then we design Search-Oriented Context Management (SOCM), which externalizes the evolving state into Frontier Task, an Evidence Graph, a Coverage Map, and Failure Memory. Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents and continuously refills freed slots with tasks targeting unresolved coverage gaps to improve utilization and throughput. To schedule and control the execution of search agents, SearchOS introduces a Search Tool Middleware Harness that intercepts model and tool interactions to record grounded evidence and react to stalls or budget exhaustion, and provides a reusable hierarchical skill system comprising strategy and access skills to augment the agents' search process and avoid repeating failed search patterns across runs. On WideSearch and GISA, SearchOS leads all metrics among the evaluated single- and multi-agent baselines, paving the way toward robust information-seeking collaboration.

LLM agents that invoke privileged tools are vulnerable to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved data hijack the agent's actions. A growing body of work evaluates defenses against IPI, but the validity of that evaluation is rarely examined. We audit an IPI benchmark and its harness and identify four defect classes -- silent payload non-delivery, attack success scored by tool identity rather than arguments, false-rejection rate conflated with model incapacity, and the absence of an audit trail -- each of which yields a plausible, publishable, and incorrect number. We quantify the distortion by re-scoring identical execution traces under the defective and corrected definitions: on real agent behaviour, the tool-identity scorer reports a 21.7% attack-success rate where the true argument-level rate is 1.2%. In the sharpest case, an open model previously reported at 62.8% registers 0% under the corrected harness -- the prior figure largely an artifact of undelivered payloads and identity-level scoring. We release a harness whose construction makes each defect unrepresentable -- machine-checkable payload placement, argument-level attacker predicates, per-scenario environments, and mandatory trace persistence -- and use it to report three quantities the field does not: whether a compromised agent discloses the attack, the full security/utility operating curve of an LLM-judge defense, and tool-calling capability disentangled from defensive over-blocking. A corrected harness further overturns a reported "capability barrier": a model deemed incapable of tool use is in fact fully capable, its earlier result an artifact of environment mismatch. We argue that evaluation validity is a prerequisite for, not a footnote to, defense claims in agentic security, and provide an instrument that enforces it.

LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results. We introduce the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism, decision determinism, and evidence-conditioned faithfulness in tool-using agents deployed in financial services. Across 4,700+ agentic runs (7 models, 4 providers, 3 financial benchmarks with 50 cases each at T=0.0), we find that decision determinism and task accuracy are not detectably correlated (r = -0.11, 95% CI [-0.49, 0.31], p = 0.63, n = 21 configurations): models can be deterministic without being accurate, and accurate without being deterministic. Because neither metric predicts the other in our sample, both must be measured independently, which is precisely what DFAH provides. Small models (7-20B) achieve near-perfect determinism through rigid pattern matching at the cost of accuracy (20-42%), while frontier models show moderate determinism (50-96%) with variable accuracy. No model achieves both perfect determinism and high accuracy, supporting DFAH's multi-dimensional measurement approach. We provide three financial benchmarks (compliance triage, portfolio constraints, and DataOps exceptions; 50 cases each) together with an open-source stress-test harness. Across these benchmarks and DFAH evaluation settings, Tier 1 models with schema-first architectures achieved determinism levels consistent with audit replay requirements.

Multimodal Foundation Models (MFMs) have made substantial progress, yet remain fragile in spatial reasoning over the physical world. A key bottleneck lies in their inability to transform local egocentric observations into a global allocentric spatial representation. To address this, we propose AlloSpatial, an agentic framework for allocentric spatial cognition in foundation models. AlloSpatial introduces World2Mind, a plug-and-play cognitive mapping sandbox that converts egocentric observations into structured allocentric priors, including Allocentric-Spatial Trees and route maps that support querying object topology, geometric relations, passability, and trajectories. To utilize these priors reliably under noisy reconstruction and ambiguous visual evidence, AlloSpatial introduces a Spatial Reasoning Harness for tool-use judgment, modality-decoupled cue collection, and geometry-semantic arbitration. We further internalize this process in Qwen3-VL through cold-start reinforcement learning with a harness-gated trajectory-level reward. Experiments on VSI-Bench and MindCube show that AlloSpatial improves proprietary models by 5%-18% in a training-free setting, while ASTs alone support strong spatial reasoning even when visual inputs are removed. The trained AlloSpatial agents further outperform larger general-purpose models and competitive spatial baselines, suggesting that structured allocentric representations, active tool use, and verifiable reasoning offer a promising route toward spatially capable foundation models.

Building a deep research agent today is an exercise in glue code: the same backbone evaluated on the same benchmark can report different accuracies in different papers because harness and tool registry all differ, and integrating a new foundation model into a comparable evaluation surface costs weeks of model-specific engineering. We call this the per-paper engineering tax and release BioMedArena, an open-source toolkit that not only alleviates it but also provides an arena for fair comparison of different foundation models when evaluating them as deep-research agents. BioMedArena decouples six layers of biomedical agent evaluation -- benchmark loading, tool exposure, tool selection, execution mode, context management, and scoring -- and exposes 147 biomedical benchmarks and 75 biomedical tools across 9 functional families. Adding a new model, benchmark, or tool reduces to registering a few-line provider adapter. We further provide 6 agent harnesses with 6 context-management strategies, which provide 12 backbones with competitive research capabilities and significantly improved performance, achieving state-of-the-art (SOTA) results on 8 representative biomedical benchmarks, with an average lift of +15.03 percentage points over prior SOTA. The toolkit, configurations, and per-task traces are available at https://github.com/AI-in-Health/BioMedArena

Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending entities, post-cutoff events, and more. This world-knowledge bottleneck is structural: generators are trained on fixed corpora, but the visual world is open-ended. We construct SearchGen-20K and SearchGen-Bench, with 20,839 prompts spanning twelve failure categories and twenty-two domains, paired with a pre-executed multimodal SearchGen-Corpus-1M to support offline, reproducible research. On SearchGen-Bench, frontier open generators score only 21 to 28 out of 100, a 40-point collapse invisible to existing benchmarks. The natural remedy is to employ search tools, enabling agentic visual generation. However, we find that naive search fails: it retrieves indiscriminately, injecting noise into prompts the generator already handles. We trace the root cause to a generator-specific, evolving knowledge boundary: the divide between what a generator can internalize through training and what must remain in external context. Although this boundary is hard to specify in advance, we show that it is discoverable through a teach-then-search co-training framework. Even a minimal version of this co-training recipe produces monotonic improvement, laying the foundation for recursive self-improvement in visual generation that can meet world-knowledge-grounded requests. We release the full dataset, co-training corpus, and search corpus as a replayable harness for tool-augmented, world-knowledge-grounded visual generation.

Recent advances in agentic visualization have enabled the translation of natural language into executable scientific visualization (SciVis) workflows. While general-purpose coding agents show strong capabilities, they often lack the tool-specific expertise required for SciVis tasks. In this work, we present SciVisAgentSkills, a collection of reusable agent skills that augment coding agents for scientific data analysis and visualization by encoding environment assumptions, tool usage patterns, and domain heuristics across scientific tools such as ParaView, napari, VMD, and TTK. We evaluate these skills on Codex and Claude Code using SciVisAgentBench, a benchmark of 108 expert-designed multi-step tasks. Results show that agent skills improve mean task scores across the evaluated suites, with token-efficiency benefits that depend on the agent harness and tool setting. These findings highlight the importance of structured procedural knowledge for enabling reliable, long-horizon SciVis workflows, while also showing that skills should be studied alongside the execution harness that loads and applies them. The skills are available at https://github.com/KuangshiAi/SciVisAgentSkills.

Trustworthy deployment of LLM-based agents in software systems requires evaluating how they perform on application-specific workflows, with enough granularity to localize where they succeed and fail. Yet existing agent evaluation mechanisms are limited: benchmarks have low construct validity for application-specific workflows and environments, and replica evaluation environments are expensive and prone to drift. We propose Copy-on-Write (CoW) Scoring, a framework that evaluates agent operations directly within application environments using a PostgreSQL-level Copy-on-Write mechanism to isolate agent writes. CoW Scoring produces session- and operation-level scores that highlight where agents' database write operations succeed and fail in a given application environment, enabling inexpensive evaluation and iteration on agent harnesses and tool surfaces. We demonstrate the framework on Plane, an open-source project-management platform, where analysis surfaced specific issues in the tool surface, and corresponding fixes produced measurable improvements on affected models. Python library: https://github.com/trail-ml/agent-cow-python

Keyword-matching benchmarks can credit small models for tool use they never perform. We document such a false positive in a matched-architecture pair of Spanish security language models and propose a ladder of strict, cheap diagnostics. A 661.6M parameter model (approx. 65% code/technical text; no dedicated SFT) and a 1,109M model (web-heavy multi-phase curriculum; 6B-token tool-SFT) share decoder, tokenizer, and special tokens, scoring almost identically on lenient tool-use metrics (B4: 0.660 vs. 0.650). Verbatim-reproduction checks on training examples separate them completely: the 600M emits valid tool calls with generalized arguments on 6/6 examples; the 1B does so on 0/6 across checkpoints. A first-token probe localizes the 1B's failure to a missing prior (prob. 10^{-4}--10^{-5} on <|tool_call|>), which was erased by its web-heavy training phase. A targeted SFT recipe (diverse corpus, 5x higher learning rate, 2,202 steps, ~3.3 GPU-hours) repairs the 1B using three orders of magnitude fewer tokens than the failed phase. On all 269 corpus rows, valid emission rises from 0.100 to 0.959 (600M: 0.926). On 238 unseen prompts, the repaired 1B passes 0.536 vs. the 600M's 0.428 (p = 0.004). Embedding-drift checks show the repair did not move the trigger token's tied embedding (97.7% of the bf16 table remains bit-identical), meaning changes live in the surrounding network. Both models over-trigger, rarely answering negative prompts without a call (0.09 for 600M, 0.17 for repaired 1B). Factorial analyses confirm all repair configurations install the format, though suppression benefits from a diverse corpus remain a hypothesis due to seed sensitivity. This cheap diagnostic ladder costs minutes of CPU time and should gate tool-use claims on small models.

Phone agents are increasingly expected to complete real mobile workflows rather than merely predict the next screen action. However, much of the current mobile-agent literature still evaluates agents primarily as GUI controllers that observe a screen, emit taps and swipes, and are scored by target app state. Real phone-use tasks are broader: they require deciding when to use app GUIs, device-side commands, or structured tools, while leaving evidence that the intended side effect actually occurred. We introduce PhoneHarness, a mixed-action benchmark and execution harness for studying phone-use agents on verifiable mobile workflows. PhoneHarness runs a device-side agent loop over GUI, CLI, and host-side tool actions, combining deterministic action routing with bounded GUI delegation and auditable execution traces. Its benchmark, PhoneHarness Bench, evaluates whether agents complete tasks with observable side effects, not only whether they produce plausible final answers. On the annotated evaluation split, PhoneHarness reaches a 75.0% pass rate, outperforming the strongest non-PhoneHarness settings by 12.9 percentage points. PhoneHarness and PhoneHarness Bench therefore play distinct but mutually dependent roles: the harness makes mixed phone workflows executable, while the benchmark measures whether agents can use that harness reliably and safely. Our findings suggest that reliable phone automation depends on action-surface routing and verifiable execution, not only visual GUI control.

Recent work on LLM-driven autonomous penetration testing reports promising results, but existing systems often bundle architectural, prompting, and tool-integration choices together. This makes it difficult to determine what is gained over a simple agent and harness. We present Cochise, a 630 LOC Python reference implementation for autonomous penetration-testing experiments. Cochise connects to a Linux execution host over SSH and supports attacking controlled target environments reachable from that jump host. The prototype implements a Planner--Executor architecture in which long-term state is maintained by the planner, while a ReAct-style executor issues commands over SSH and self-corrects based on command outputs. The scenario prompt can be adapted to different target environments. We evaluate the harness against a live third-party testbed, Game of Active Directory (GOAD). Cochise is intended not as a state-of-the-art penetration-testing agent, but as a reusable experimental infrastructure for comparing models, agent architectures, and penetration-testing traces. Alongside the prototype, we release replay and analysis tools: (i) cochise-replay for offline visualization of captured runs, (ii) cochise-analyze-logs and cochise-analyze-graphs for cost, token, duration, and compromise analysis, and (iii) a corpus of JSON trajectory logs from GOAD runs, so that researchers can study agent behavior without provisioning the 48--64 GB RAM / 190 GB storage testbed themselves. Tool demo video available at https://youtu.be/2mQimB1ufyI.

In this work, we unveil a novel tool for generating Italian crossword puzzles from text, utilizing advanced language models such as GPT-4o, Mistral-7B-Instruct-v0.3, and Llama3-8b-Instruct. Crafted specifically for educational applications, this cutting-edge generator makes use of the comprehensive Italian-Clue-Instruct dataset, which comprises over 30,000 entries including diverse text, solutions, and types of clues. This carefully assembled dataset is designed to facilitate the creation of contextually relevant clues in various styles associated with specific texts and keywords. The study delves into four distinctive styles of crossword clues: those without format constraints, those formed as definite determiner phrases, copular sentences, and bare noun phrases. Each style introduces unique linguistic structures to diversify clue presentation. Given the lack of sophisticated educational tools tailored to the Italian language, this project seeks to enhance learning experiences and cognitive development through an engaging, interactive platform. By meshing state-of-the-art AI with contemporary educational strategies, our tool can dynamically generate crossword puzzles from Italian educational materials, thereby providing an enjoyable and interactive learning environment. This technological advancement not only redefines educational paradigms but also sets a new benchmark for interactive and cognitive language learning solutions.

Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use offers a promising alternative to end-to-end vision-language-action systems by combining high-level reasoning with external modules for perception, planning, and control. However, it remains unclear what makes an effective harness for embodied manipulation, and to what extent such a harness can unlock embodied capabilities in a wide range of reasoning models. In this work, we present Guava, a harness framework for embodied tool use developed through systematic exploration of the design space of agent workflows, action spaces, and observation spaces. Our study identifies three key ingredients for effective embodied agents: iterative perception-reasoning-action loops, semantic action abstractions, and multimodal observations. To understand whether these design principles are universal even to small models, we develop an end-to-end training pipeline that distills embodied manipulation capabilities into a 4B open-source model using fewer than 2K trajectories collected entirely in simulation. Experimental results in both simulation and real-world environments show performance comparable to frontier proprietary models while exhibiting strong generalization to unseen objects, novel instructions, and long-horizon tasks. Results suggest that a well-designed harness can serve as a scalable, model-agnostic interface for embodied manipulation, enabling strong emergent embodied capabilities in compact open-source models with minimal training data.

Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task's context. We study whether task feedback can instead turn recurring control into reusable executable code, while reserving LLM calls for task-specific semantic reasoning. We introduce Growing Harness, a failure-guided training paradigm that learns the agent harness itself from a strategy-free scaffold that exposes fixed model and tool interfaces but encodes no task-solving controller. Function-level execution traces localize each failure to a bounded code surface, an optimizer repairs a window of failures jointly, and a success-first held-out gate rolls back repair sequences that harm prior capability. Accepted edits accumulate in one shared harness, allowing its control structure to emerge from task feedback. Across BrowseComp-Plus and WebArena-Verified with three deployment models from 4B to 120B parameters, Growing Harness achieves the highest mean success in five of six benchmark-model settings and trails the best mean by 0.7 pp. in the sixth. Relative to a Tool-Calling agent, it reduces LLM calls by 76.0-91.8% and deployed-agent inference cost by 74.4-98.6%. On WebArena-Verified, its success remains 44.7-45.3% across model scales, whereas Tool-Calling falls to 6.7% with the 4B model. Ablations show that trace-local edits, joint repair, and gate-based rollback each improve final success. These results show that persistent program growth can move recurring control out of model context and into low-cost code, yielding reusable specialist agents that remain effective with smaller deployment models.

Agent skills extend language-model agents with task-specific procedures, scripts, and references, but the tasks and environments they target continually change. Existing methods improve skills in bounded runs and retain only the final artifact, discarding the decision history that later agents need to interpret prior revisions, evaluations, and rejected alternatives. We introduce SkillHone, a harness for continual agent skill evolution grounded in persistent decision history. SkillHone pairs skill revisions with evaluation-side evidence that supplies practice feedback, recording structured histories of diagnoses, revisions, evidence, and outcomes. Role-separated subagents run candidate skills on practice probes with redacted reporting and propose revisions informed by prior decisions, enabling cross-session refinement without rediscovering past rationale. On deep-research benchmarks, SkillHone runs without a pre-integrated search stack and outperforms the commercially backed deep-research agent by 15.8 points on GAIA and 3.2 points on WebWalkerQA-EN, while also exceeding prior skill-evolution methods. We further deploy SkillHone on internal tool-mediated analysis scenarios, where it improves accuracy by an average of 18.8 points across seven settings.

What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psychology to study how well agents adapt to hidden reliability shifts. Our benchmark mounts tool-skill libraries with redundancies, where many tools solve the same task but differ in hidden reliability. In our evaluation framework, a branched schedule shifts the reliable tool group at hidden boundaries and pairs every shift with a no-shift control. We find that agents, by default, settle on a small recurring routine within a few turns of each boundary, with call shares concentrating on a few discrete values after each reliability shift. We score the set-shifting accuracy for each agent trajectory: the joint probability of routing to the target tool group in every post-shift window. We test open-weight LLMs in an open-source agentic harness and find qualitatively distinct failure modes across the same set of routines. We also find that set framing, how the toolset presents the alternatives as competing or complementary, shifts the routing dynamics.

Large language models have become capable reasoners and tool users that write and run code and search the literature, which makes automating the research process itself a realistic goal. We present PAPERCLAW, a harnessed multi-agent system that carries a project autonomously, from a field of study to a finished paper. PAPERCLAW curates a domain from a field's live literature, datasets, and code; brainstorms it into an idea with a pre-registered main-result contract; and drives a stoppable hypothesis map through an iterative propose, test, reflect loop that grows only from measured verdicts and halts once the evidence supports the idea, at which point it writes a venue-compliant paper. A full-lifecycle memory keeps each stage in a single living record, so a long run can be paused, inspected, and resumed without losing context. At the centre is an in-cycle research assistant with research tools and skills: it can drive the whole pipeline on its own, while the same interface lets a person step in at any stage, turning a first autonomous draft into a stronger paper through human-in-the-loop refinement. Throughout, PAPERCLAW keeps its output grounded and checkable, citing only references validated against open scholarly indexes and reporting results that genuinely ran. An evaluation with an LLM judge finds that PAPERCLAW produces strong papers both fully autonomously and with human-in-the-loop refinement.

Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or experiments, and judgement that links a new question to an old result. This experience is essential for reproducibility and knowledge transfer, yet it is usually fragmented across notebooks, repositories, job logs and individual memory, and it is rarely portable across artificial-intelligence agents. Here we argue that a lifelong AI partner for materials science can be designed around persistent memory rather than around a particular agent implementation. We introduce a self-evolving memory framework that stores scientific experience as inspectable facts and executable skills, so that observations, failure boundaries, protocols and validation checks can be retrieved, revised and migrated across models. We evaluate the idea in three computational settings that expose different layers of materials-research competence. In 49 real-world materials-tool-use questions comprising 138 executable subtasks, memory nearly doubles GPT-5.2 task success without model-parameter updates. In elemental-solid equation-of-state calculations, memory converts a wavefunction-initialization failure into a pre-execution guardrail, improving outcomes from 22/1/4 to 25/2/0 Correct/Partial/Error and avoiding 92% of repeated errors. In 13 practical material simulation workflows, remembered skills and failure facts halve the aggregate trace burden (tokens) and reduce tool calls by over a factor of two by the third round, while preserving physically meaningful outputs in band-gap, phonon, vacancy and work-function analyses. These results show that agent memory can serve as a durable scientific asset; a portable, self-improving record of materials-research experience that outlives any single model or agent stack.

While Large Language Models (LLMs) have demonstrated enhanced capabilities in function-calling, these advancements primarily rely on accessing the functions' responses. This methodology is practical for simpler APIs but faces scalability issues with irreversible APIs that significantly impact the system, such as a database deletion API. Similarly, processes requiring extensive time for each API call and those necessitating forward planning, like automated action pipelines, present complex challenges. Furthermore, scenarios often arise where a generalized approach is needed because algorithms lack direct access to the specific implementations of these functions or secrets to use them. Traditional tool planning methods are inadequate in these cases, compelling the need to operate within black-box environments. Unlike their performance in tool manipulation, LLMs excel in black-box tasks, such as program synthesis. Therefore, we harness the program synthesis capabilities of LLMs to strategize tool usage in black-box settings, ensuring solutions are verified prior to implementation. We introduce TOPGUN, an ingeniously crafted approach leveraging program synthesis for black box tool planning. Accompanied by SwissNYF, a comprehensive suite that integrates black-box algorithms for planning and verification tasks, addressing the aforementioned challenges and enhancing the versatility and effectiveness of LLMs in complex API interactions. The public code for SwissNYF is available at https://github.com/iclr-dummy-user/SwissNYF.

Creative AI is moving from single-step asset generation toward long-horizon multimodal production. Although recent generative models can synthesize high-quality images, videos, audio clips, UI elements, storyboards, slides, and other creative assets, real-world creative work requires more than isolated prompt-output interactions. It involves references, drafts, alternatives, edits, failed attempts, version relations, tool actions, evaluation signals, and human feedback, which together form an evolving project state. Existing prompt-based, chat-based, and node-based generation systems only partially support this state, as they often discard intermediate context, rely on linear conversations, or require manually specified workflows. Recent commercial systems indicate a shift toward agent-assisted creative production, but their closed architectures make it difficult to study how agents represent context, choose tools, revise artifacts, recover from failures, and maintain consistency over time. To address this gap, we introduce JarvisHub, a canvas-native creative agent harness for long-horizon multimodal creation. JarvisHub treats an editable canvas as the user workspace, the agent's external memory, action space, and shared project state, representing multimodal artifacts, dependencies, versions, and feedback as typed canvas nodes and links. Through a three-layer architecture of canvas state, protocol bridge, and agent runtime, JarvisHub enables agents to act within an inspectable and editable creative state. This design moves creative agents beyond isolated tool use toward sustained, human-steerable creative automation, where agents can progressively plan, generate, revise, and organize multimodal projects while users remain able to inspect, guide, and intervene throughout the process.

Whole-Slide Image (WSI) is an important tool for evaluating the prognosis of cancer patients. Present WSI-based prognosis studies generally follow a conventional paradigm -- cancer-specific model development -- where one cancer disease corresponds to one model and this model cannot make use of the prognostic knowledge from others. Despite its notable success in recent years, this paradigm has inherent limitations and has always been struggling with practical requirements: (i) scaling to the rare tumor diseases with very limited samples and (ii) benefiting from the generalizable prognostic knowledge in other cancers. To this end, this paper presents the first systematic study on Prognostic Knowledge Transfer in Pathology, called Path-PKT. It comprises three main parts. (1) We curate a large dataset (UNI2-h-DSS) with 13 cancers and use it to evaluate the transferability of prognostic knowledge between different cancers computationally. (2) We design experiments to understand what factors affect knowledge transfer and what causes positive transfers. (3) Motivated by empirical findings, we propose a new baseline approach (MoE-PKT) with a routing mechanism to utilize the generalizable prognostic knowledge in other cancers. Finally, we show the transferability of source models to rare tumor diseases. This study could lay solid foundations for the study of knowledge transfer in WSI-based cancer prognosis. Source code is available at https://github.com/liupei101/Path-PKT.

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. Since both the harness and model weights shape behavior, we ask how harness evolution and lightweight fine-tuning should be combined. Across seven enterprise agent tasks, we first evolve a harness with the weaker model, then find that a stronger expert often uses it more effectively, suggesting expert supervision could close the remaining gap. However, training the weaker model on the expert's complete trajectories under the evolved harness backfires: performance regresses on all seven tasks by 4 to 30 points across Qwen3-Coder and Gemma 4, even though the same procedure helps under the unevolved harness. Our analysis shows that imitation transfers knowledge and increases scaffold usage, but disrupts model-harness fit: the weaker model adopts the expert's planning strategy without the competence to execute it and no longer matches the harness evolved around its native planning style. We therefore develop an on-policy expert-correction pipeline, automated by a meta-level MLE agent, that localizes the failing turn in the weaker model's own rollout and asks the expert to rewrite only that turn. This preserves the model's planning style and combines the gains of harness evolution and model adaptation. Our results identify and resolve a source of contention between harness and weight updates, yielding a compatibility-preserving recipe for economical co-evolution on domain-specific enterprise tasks.

Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within a growing context, making the state difficult to track and allowing incorrect self-assessments to propagate into later decisions. We reformulate long-horizon execution as a task-state management problem and propose LongHorizon-Harness, which maintains the task state explicitly outside execution and updates it only with facts independently verified from the environment. Its Manage-Execute-Audit(MEA) loop uses a manager to maintain the task state and determine the next subtask, a fresh-context executor to perform it, and a read-only auditor to verify the resulting environment state before the next round. A lightweight AgentAdapter supports interchangeable model and harness backends without modifying their native agent loops. LongHorizon-Harness improves Qwen~3.7-Plus from 51.8% to 80.7% on WeaveBench, from 69.7% to 77.2% on Terminal-Bench~2.1, and from 2.8% to 8.3% on OSWorld~2.0. It also raises Claude Opus~4.7 from 20.0% to 34.3% on an OSWorld2.0 subset, demonstrating consistent gains across models, harnesses, and interaction domains.

Hybrid computer-use agents can act through screenshots or call text tools. We find that having a tool available does not settle which way the effect goes. Under one identical GUI-MCP harness on the OSWorld-MCP benchmark (309 tasks), the same MCP tools improve a reasoning model by +4.0pp and degrade a non-reasoning model by -5.9pp (5 runs each, both beyond 2 SE). What separates the two is tool-decision behavior. The non-reasoning policy ignores, misnames, or falsely terminates around tools. The reasoning model avoids these failures, yet still calls a tool on only 55/309 tasks, 23.9% of the tool-reachable ones. We call this shortfall the adoption gap. Both levels of the problem share one cause: the model already has a cheaper route and is never trained to take it. Multi-turn RL probes that cause. At the action level, a dense tool bonus raises spreadsheet adoption 0.03 -> 0.33 and carries into greedy decoding, but held-out accuracy does not follow. Behavior is steerable; competence is not. The bottleneck lies in tool-call semantics. At the context level, a successful tool call often makes the next screenshot redundant. Dropping it and halving image history cuts input tokens by about a third, at a small accuracy cost. Retraining under the same observation rule removes that cost. The compressed agent then reaches 37.8% against 33.0% for the uncompressed operating point, at 53% of the input cost, and closes the rich-lean gap on a pre-registered degraded subset to zero. Tools help when the model chooses and integrates them, and current hybrid agents leave many such choices unused. Code and checkpoints: https://github.com/redai-infra/hybrid-routing-agent

Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execution feedback. However, the native execution environments of these harnesses are inherently misaligned with policy-gradient training: environmental crashes and reward hacking corrupt outcome signals, while train-inference discrepancies decouple rollout behavior from policy updates. To address this, we present LEGO-RL, a framework that bridges native coding-agent harnesses with scalable policy-gradient optimization without modifying their internal control flow. LEGO-RL is built upon three pillars: (1) faithful optimization via in-process LLM proxying that captures raw generation streams for token-level alignment and robust trainer-side log-probability recomputation, even under harness-side compaction or re-serialization; (2) reliable execution via scalable sandbox orchestration featuring image caching and stage-wise defenses to mitigate reward hacking; and (3) observable training through an integrated plugin that automates validation and monitoring, paired with a Live UI for granular trajectory diagnostics. We evaluate LEGO-RL by training the sparse MoE model Qwen3.5-35B-A3B with GSPO across three native coding-agent harnesses. LEGO-RL improves Qwen3.5-35B-A3B across OpenHands SDK (64.0% to 70.4%), Claude Code (62.4% to 68.2%), and OpenCode (57.2% to 66.6%) on SWE-bench Verified, while maintaining a rollout-training probability correlation above 0.99.

Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study agent harness distillation: using a domain- or instance-optimized harness as training-time guidance and transferring the behaviors it induces into model weights, so that its gains survive under a single fixed target harness. The challenge is that the two harnesses differ in action space and available information, so guidance from the optimized harness cannot serve directly as supervision for the target one. We introduce Harness-Zero, which enables harness distillation through agent-as-harness. Guided by the optimized harness, a harnessing agent corrects student responses before execution in the target harness's action space, turning harness guidance into training demonstrations. Fine-tuning on the resulting trajectories internalizes harness-induced behavior into the model, so the specialized harness can be removed at deployment. Our experiments spanning knowledge work, tool use, and science domains show that: (1) For frontier LLMs using the same evolved harness, agent-as-harness outperforms code-as-harness. (2) With the specialized harness removed at deployment, Harness-Zero improves the base model's macro-average task success from 23.3% to 44.3%, even exceeding the 41.7% it reaches with that harness still attached. (3) Harness-Zero recovers harness-induced behaviors absent from the base model, with 82.3% average recovery across 28 patterns in the three domains.

Tool-calling LLM agents are increasingly deployed in enterprise applications. However, effective evaluation and optimization require high-quality, diverse task datasets that are often difficult to obtain due to privacy and other constraints. Existing synthetic task generation methods often produce generic tasks that ignore an agent's underlying state or database and fail to reflect real-world usage diversity. We propose EdgeGen, a synthetic task generation framework that extracts compliance rules from an agent's specification and uses them to generate database-grounded edge-case tasks designed to violate these rules. When combined with existing synthetic data generation techniques, EdgeGen enables agent improvement through finetuning and harness optimization. The resulting pipeline forms a fully automated closed-loop system that requires no human annotation. Finetuning on data generated by EdgeGen yields a consistent mean progress improvement of 2 percent to 42 percent on tau2bench airline domain, while other baseline methods show degradation for some models. On the other hand, for harness optimization, our method shows a mean progress improvement of 10 percent and 30 percent over the human-curated and base harnesses, respectively, for the Gemma-4-e4b model.

Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. However, existing methods primarily optimize how the harness is updated while largely fixing which training scenarios generate the feedback that drives those updates. As the harness evolves, the scenarios most useful for further optimization can change, suggesting that the training curriculum itself should adapt alongside the harness. We formulate this missing dimension of harness optimization as an automated curriculum learning problem and introduce ActiveSaddler. ActiveSaddler models the evolving curriculum as a non-stationary bandit with dynamically instantiated optimization targets. It abstracts recurring failures into reusable failure-pattern arms, estimates the potential learning progress from further targeting each pattern, and adaptively balances revisiting known weaknesses with exploring unseen scenarios for new ones. Optimization outcomes continually update both the set of discovered failure patterns and their priorities, allowing the curriculum to co-evolve with the harness. Experiments on GAIA2 and Terminal-Bench 2.0 show that ActiveSaddler consistently discovers stronger harnesses, improving test Pass@1 by 4.4 and 7.5 percentage points over the same harness optimizer using a scenario order fixed before optimization, respectively. Ablations further show that these gains depend on dynamically constructing optimization targets, estimating their evolving utility, and balancing continued optimization with new failure discovery. Together, these results establish automated curriculum learning as a new crucial optimization dimension for harness optimization.

Reinforcement learning from human feedback (RLHF) has emerged as a central tool for language model alignment. We consider online exploration in RLHF, which exploits interactive access to human or AI feedback by deliberately encouraging the model to produce diverse, maximally informative responses. By allowing RLHF to confidently stray from the pre-trained model, online exploration offers the possibility of novel, potentially super-human capabilities, but its full potential as a paradigm for language model training has yet to be realized, owing to computational and statistical bottlenecks in directly adapting existing reinforcement learning techniques. We propose a new algorithm for online exploration in RLHF, Exploratory Preference Optimization (XPO), which is simple and practical -- a one-line change to (online) Direct Preference Optimization (DPO; Rafailov et al., 2023) -- yet enjoys the strongest known provable guarantees and promising empirical performance. XPO augments the DPO objective with a novel and principled exploration bonus, empowering the algorithm to explore outside the support of the initial model and human feedback data. In theory, we show that XPO is provably sample-efficient and converges to a near-optimal language model policy under natural exploration conditions, irrespective of whether the initial model has good coverage. Our analysis, which builds on the observation that DPO implicitly performs a form of Q^{star}-approximation (or, Bellman error minimization), combines previously disparate techniques from language modeling and theoretical reinforcement learning in a serendipitous fashion through the perspective of KL-regularized Markov decision processes. Empirically, we find that XPO is more sample-efficient than non-exploratory DPO variants in a preliminary evaluation.

We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include prompt and task framing, tool interfaces, skills, MCP-backed providers, subagent structure, and agent-loop configuration. StarHarness constructs a compact evolution pool by stratifying tasks according to baseline failure behavior, separates proposer-visible search tasks from proposer-hidden selection tasks, and reserves held-out tasks for evaluating generalization. Across ITBench SRE, EnterpriseOps-Gym ITSM, and AutomationBench Finance, harness evolution improves full-benchmark performance by 20-35 percentage points over the default harness after 4-12 accepted changes per environment. These gains persist on tasks excluded from evolution and transfer without re-evolution across GPT and Qwen model families. Trace analysis links the improvements to interface repairs, environment conventions, and operational knowledge that compresses search, with fewer false-positive diagnoses and shorter trajectories in several settings. StarHarness therefore offers a practical way to reduce persistent model-environment mismatch in tool-rich enterprise tasks.

LLMs have demonstrated significant potential in code generation tasks, achieving promising results at the function or statement level across various benchmarks. However, the complexities associated with creating code artifacts like classes, particularly within the context of real-world software repositories, remain underexplored. Prior research treats class-level generation as an isolated task, neglecting the intricate dependencies & interactions that characterize real-world software environments. To address this gap, we introduce RepoClassBench, a comprehensive benchmark designed to rigorously evaluate LLMs in generating complex, class-level code within real-world repositories. RepoClassBench includes "Natural Language to Class generation" tasks across Java, Python & C# from a selection of repositories. We ensure that each class in our dataset not only has cross-file dependencies within the repository but also includes corresponding test cases to verify its functionality. We find that current models struggle with the realistic challenges posed by our benchmark, primarily due to their limited exposure to relevant repository contexts. To address this shortcoming, we introduce Retrieve-Repotools-Reflect (RRR), a novel approach that equips LLMs with static analysis tools to iteratively navigate & reason about repository-level context in an agent-based framework. Our experiments demonstrate that RRR significantly outperforms existing baselines on RepoClassBench, showcasing its effectiveness across programming languages & under various settings. Our findings emphasize the critical need for code-generation benchmarks to incorporate repo-level dependencies to more accurately reflect the complexities of software development. Our work shows the benefits of leveraging specialized tools to enhance LLMs' understanding of repository context. We plan to make our dataset & evaluation harness public.

LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and write files, call tools, and reuse workspace state across sessions. While such capabilities enhance utility, they also expose a new attack surface for attackers. Attackers can embed a prompt injection within a file or tool output. Agents may read this hidden instruction, store it, and execute it later. In this multi-step trojan attack paradigm, no individual step appears malicious on its own, but these steps can collectively turn untrusted text into persistent control content. However, existing defenses often inspect each step in isolation. As a result, they can block a clear harmful action, but fail to detect the earlier write operation that plants the backdoor. To reveal this threat, we introduce ClawTrojan, a benchmark designed to identify multi-step trojan attacks in local agentic harnesses. In an OpenClaw-style simulated workspace with GPT-5.4, ClawTrojan reaches a 95.5% attack success rate (ASR), while existing single-turn prompt-injection attacks produce near-zero ASR on the same model. To address this threat, we propose DASGuard, which scans control-like text in sensitive local files, traces its origin, and removes control content that does not originate from a trusted source. Our results show that DASGuard achieves strong dynamic defense by combining runtime attack blocking with sanitized commits to the workspace.

LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the base model, but also on the harness: the system layer that manages context, tools, state, constraints, permissions, tracing, and recovery. However, existing benchmarks typically abstract away execution, compare complete agent systems, or hold the harness fixed, making execution-layer variation difficult to study. We introduce Harness-Bench, a diagnostic benchmark for evaluating configuration-level harness effects in realistic agent workflows. Harness-Bench evaluates representative harness configurations across multiple model backends under shared task environments, budgets, and evaluation protocols, while preserving each harness's native execution behavior. The benchmark contains 106 sandboxed offline tasks constructed from practical agent-use patterns and manually reviewed for realism, solvability, oracle-checkability, and integrity. Each run records final artifacts, execution traces, usage statistics, and validator outputs, enabling analysis beyond final completion. Across 5,194 execution trajectories, we observe substantial variation in completion, process quality, efficiency, and failure behavior across model-harness pairings. These results suggest that agent capability should be reported at the model-harness configuration level rather than attributed to the base model alone. Our analysis further identifies recurring execution-alignment failures, where plausible reasoning becomes decoupled from tool feedback, workspace state, evidence, or verifiable output contracts. Harness-Bench provides a reproducible foundation for diagnosing and improving reliable, efficient, and auditable agent execution stacks.

Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete. We formalize this substrate as an AI Harness Engineering and identify eleven component responsibilities: task specification, context selection, tool access, project memory, task state, observability, failure attribution, verification, permissions, entropy auditing, and intervention recording. We operationalize the harness through a four-level ladder (H0-H3) that progressively exposes runtime support to the agent, and we propose a trace-based evaluation protocol that converts each agent run into an auditable episode package. Applied to a controlled validation task, the framework yields episode packages whose evidence structure varies systematically with harness level: lower levels produce only a final patch, higher levels produce reproduction logs, failure attributions, deterministic requirement checks, and structured verification reports. The framework reframes the central question of autonomous software engineering from whether a foundation model can produce a patch to whether the model-harness-environment system can produce a verifiably correct, attributed, and maintainable change. We outline a research program for the runtime systems that foundation-model software agents will require.

Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value. Falling per-token prices mask the pattern; total spend rises anyway. We argue the decisive lever against token maxing is the harness: the orchestration layer that assembles context, exposes tools, sequences turns, delegates work, and carries enterprise observability and governance. We isolate it with a controlled swap: 22 locked evaluation tasks, six foundation models (Claude Sonnet 4.6, Gemini 3.1, Gemini Flash 3.5, Qwen 3.6, GLM 5.1, Palmyra X6), changing only the orchestration layer -- a frozen conventional production loop versus the Writer Agent Harness. Holding models constant, the harness cuts blended cost per task 41% (0.21->0.12), median wall-clock 44% (48s->27s), and tokens per task 38% (14.2k->8.8k), with task-completion quality at parity (0.78->0.81, directional at this sample size). Efficiency is model-invariant -- every model gets cheaper (33-61%) -- while quality gains are capability-dependent: a model's gain correlates almost perfectly with its baseline strength (r=0.99, n=6), a phenomenon we term harness leverage. Quality per dollar rises 82%; task-completions per million tokens rise from 54.9 to 92.0. On this workload the orchestration layer moved cost per task more than the full spread of the model menu did. We formalize token economics at the orchestration layer (including effective input price under prompt caching), detail the six mechanism families behind the effect -- cache-shape discipline to failure-spend governance -- compare six widely used agent systems on the same axes, and argue the harness is the one component whose efficiency multiplies across every model an organization runs -- present and future.

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use. However, real-world tasks are often long-horizon and involve evolving contexts containing accumulated observations, intermediate edits, failed attempts, and partially completed executions. Existing agents typically operate over raw interaction history, making task progress difficult to interpret, verify, and recover, which ultimately limits reliable long-horizon execution. In this paper, we argue that addressing this challenge requires explicitly structuring both the agent's state and workflow around a unified causal representation of task progress. We present StructAgent, a state-centered framework that introduces a unified state for maintaining compact, verifiable task progress and a structured workflow that regulates progress through verifier-backed state transitions. Building on this design, StructAgent further enables explicit progress checkpointing, evidence-driven task completion, targeted failure recovery, and tool-supported execution, while ensuring that all progress updates remain grounded in verification. Extensive experiments demonstrate that StructAgent consistently improves a wide range of LLM and VLM backbones on long-horizon computer-use tasks. On OSWorld-Verified, it improves Qwen3.5-9B from 27.0\% to 46.9\% success rate and Qwen3.5-27B from 31.6\% to 62.2\%, while achieving a new open-source state of the art of 78.9\% with MiniMax-M3. Moreover, the same framework generalizes beyond desktop environments to Minecraft, demonstrating the generality of our design.

Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system. While an ideal harness system should align with human design priors and accumulate reusable experience through empirical exploration to drive recursive self-improvement, existing paradigms remain static and fall short of this capability. In this paper, we present AutoDesign, a framework that aligns with human design priors, where a meta-harness optimizer guides a code agent to recursively improve harness based on rollout feedback. To instantiate and evaluate this framework, we focus on the academic paper-to-poster generation task and introduce PosterBench, comprising a 100-paper Main Track spanning five disciplines and PosterBench-mini, a shared 10-paper subset for controlled evaluation. On the PosterBench Main Track, AutoDesign achieves the highest score of 78.32, surpassing the closed-source commercial system Claude Design by 7.45 points. Across seven controlled code-agent-model configurations, integrating the learned DesignHarness consistently improves performance, increasing the average PosterBench Score from 54.99 to 67.39 (+12.4%). In a fully autonomous long-horizon loop, it executes 253 tool calls and 11 editing turns within 40 minutes for under $3, reaching average conference-poster quality in human evaluation. A system-blind human study further demonstrates that AutoDesign achieves the highest human preference among evaluated systems.

AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Evolvable Harnesses, whose Skills, Hooks, prompts, and tools can be updated independently of model weights, enable rapid iteration but expose a trade-off: large models adapt zero-shot yet are too slow, whereas compact models meet latency targets but overfit to fixed Harness configurations. We propose Harness-Aware Training (HAT), which trains compact models to adapt to changing Harnesses. Its key component, Harness-State Augmentation (HSA), applies task-preserving transformations to Skill identifiers and content, tool schemas, prompt structures, and Hook functions. Training proceeds in three stages: HSA-SFT learns reasoning and tool use from strong-model trajectories across diverse environments; General On-Policy Distillation restores generalization lost during SFT; and HSA-RL improves robustness to changing Harnesses through reinforcement learning in augmented environments. Across four evaluation sets, HAT achieves 94.8 on Live-Stream QA (base: 80.3; strongest general LLM: 93.0) and 94.6 on Harness-Variant QA (base: 75.4). Unlike Fixed-Harness SFT, which lowers IFEval by 7.7 points from the base model, HAT avoids this regression and reaches 83.5. On one NVIDIA H20 GPU, the optimized system delivers P50 and P95 latencies of 3.4 s and 8.1 s. Deployed in Taobao Live's digital-avatar service, it also yields positive online A/B test results for GMV and item-page views.

Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry, not merely semantic appearance. Existing prompt-driven or layout-conditioned methods improve controllability, but often lack an optimizable and verifiable spatial intermediary before visual sampling. As a result, object relations, occlusion, visibility, and camera constraints can decay during multi-round generation. This paper presents SpatialGuard, a structured layout-guided framework for complex 3D spatial text-to-image generation. SpatialGuard parses prompts into image synthesis-oriented 3D layouts through a Spatial Layout Architect, realizes them as visual conditions and candidate images through a Visual Realizer, and uses a Visual Alignment Critic to validate consistency among prompt, layout, and image. To keep constraints stable across iterations, SpatialGuard introduces a Layout Harness that organizes rule constraints, tool invocation, shared knowledge, and feedback loops around the editable layout state. This design turns complex spatial generation from implicit prompt following into a verifiable process of planning, realization, validation, and repair. Comprehensive experiments show that SpatialGuard achieves state-of-the-art performance in complex 3D spatial layout generation and improves spatial faithfulness over existing text-to-image and layout control baselines.

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We present NeoHorse-1, a family of agent-native models developed to explore this path through agentic post-training. Our system combines a heterogeneous model pool with intelligent routing, recording the predicted capability demand, selected service tier, and subsequent interaction for each user turn. These records are converted into training examples that preserve interleaved reasoning, tool calls, and harness context, and are admitted through structural validation, six-dimensional semantic evaluation, and subscene-level labeling. Routing signals organize supervised fine-tuning into a three-stage curriculum and extend to routing-guided on-policy distillation, where a teacher supervises student-generated responses under the same progression. Capability-guided allocation then converts evaluation feedback into the next training mixture, closing an evaluation-selection-update loop in which what the system learns to do shapes what it learns from next. Across eleven benchmarks covering harness-based agents, tool use, coding, and instruction following, post-training raises the macro-average from 58.94 to 64.87 at 4B and from 65.60 to 69.04 at 9B, substantially narrowing the aggregate gap between the post-trained 4B model and the 9B base model. NeoHorse-1 provides an initial prototype of this feedback-driven process and a path toward harness-mediated RSI across successive iterations.

Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actions to follow instructions or locate objects. Training-based methods face generalization challenges, while training-free methods exploit multimodal large language models (MLLMs) but often lack mechanisms to reconcile proposed actions with spatial evidence, task progress, and execution failures. We present HarnessVLN, a zero-shot, training-free framework whose Agent Harness coordinates perception, retrieval, grounding, navigation, recovery, and termination through a unified tool interface. The Harness validates planner proposals against spatial evidence, geometric feasibility, and subgoal consistency, incorporating structured tool feedback into subsequent decisions. Hierarchical event memory tracks task progress and execution history, while a persistent Spatiotemporal Graph maintains reusable spatial evidence and failure annotations for verification and recovery. A replaceable Navigation Executor converts validated targets into executable motions, allowing the same Harness protocol to support instruction-following and object-goal navigation. HarnessVLN achieves success rates of 60.8%, 53.9%, 76.0%, and 59.3% on R2R, RxR, HM3D-v2, and HM3D-OVON, respectively, surpassing prior training-free SOTA results. Humanoid deployment further demonstrates its applicability to both tasks in real-world environments. The project page is: https://harnessvln.netlify.app/.

An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from what they do. We compare stopping at the same step after longer and shorter runs of results the agent judged useless; this contrast is zero for clock- or deadline-driven stopping. Where we record their judgments, the seven agents we test call a failing source's results useless 97-100% of the time, yet most of them rarely stop on that judgment. Prompt cues change when they stop but not what they stop on. Permission to answer from memory and a reasoning mode can bring early stops regardless of evidence, a stated budget moves the 7-8B models' stops to the deadline, and a stopping rule or call cost in the prompt is followed at most partly. Stopping follows the evidence only when the harness enforces an integration step that makes the agent answer after five consecutive results it judged useless. This step raises failing-source success for every model, keeps the stopping point fixed when the budget doubles, and needs no extra judgment call when the agent states its judgments. A pre-registered replication on 300 fresh questions confirms the dissociation and the rule's effect.

The realm of High-Frequency Trading (HFT) is characterized by rapid decision-making processes that capitalize on fleeting market inefficiencies. As the financial markets become increasingly competitive, there is a pressing need for innovative strategies that can adapt and evolve with changing market dynamics. Enter Reinforcement Learning (RL), a branch of machine learning where agents learn by interacting with their environment, making it an intriguing candidate for HFT applications. This paper dives deep into the integration of RL in statistical arbitrage strategies tailored for HFT scenarios. By leveraging the adaptive learning capabilities of RL, we explore its potential to unearth patterns and devise trading strategies that traditional methods might overlook. We delve into the intricate exploration-exploitation trade-offs inherent in RL and how they manifest in the volatile world of HFT. Furthermore, we confront the challenges of applying RL in non-stationary environments, typical of financial markets, and investigate methodologies to mitigate associated risks. Through extensive simulations and backtests, our research reveals that RL not only enhances the adaptability of trading strategies but also shows promise in improving profitability metrics and risk-adjusted returns. This paper, therefore, positions RL as a pivotal tool for the next generation of HFT-based statistical arbitrage, offering insights for both researchers and practitioners in the field.

The Model Context Protocol (MCP) is rapidly becoming the standard interface for Large Language Models (LLMs) to discover and invoke external tools. However, existing evaluations often fail to capture the complexity of real-world scenarios, relying on restricted toolsets, simplistic workflows, or subjective LLM-as-a-judge metrics. We introduce MCP-Atlas, a large-scale benchmark for evaluating tool-use competency, comprising 36 real MCP servers and 220 tools. It includes 1,000 tasks designed to assess tool-use competency in realistic, multi-step workflows. Tasks use natural language prompts that avoid naming specific tools or servers, requiring agents to identify and orchestrate 3-6 tool calls across multiple servers. We score tasks using a claims-based rubric that awards partial credit based on the factual claims satisfied in the model's final answer, complemented by internal diagnostics on tool discovery, parameterization, syntax, error recovery, and efficiency. Evaluation results on frontier models reveal that top models achieve pass rates exceeding 50%, with primary failures arising from inadequate tool usage and task understanding. We release the task schema, containerized harness, and a 500-task public subset of the benchmark dataset to facilitate reproducible comparisons and advance the development of robust, tool-augmented agents.

Long-horizon language-model agents are dominated, in lines of code and in operational complexity, not by their underlying model but by the harness that wraps it: context compaction, tool caching, semantic memory, trajectory reuse, speculative tool prediction, and the glue that binds the model to a sandboxed execution environment. We argue that harness design is a first-class machine-learning problem and that automated configuration search dominates manual stacking once the flag space exceeds a handful of bits. We defend this claim in two steps. First, we formalize automated harness optimization as constrained noisy Bayesian optimization over a mixed-variable, cost-heterogeneous configuration space with cold-start-corrected rewards and a posterior chance-constrained safety check, and give a reference solver, HARBOR (Harness Axis-aligned Regularized Bayesian Optimization Routine), built from a block-additive SAAS surrogate, multi-fidelity cost-aware acquisition, and TuRBO trust regions. Second, we instantiate the problem in a flag-gated harness over a production coding agent and report a controlled four-round manual-tuning case study against a fixed task suite and an end-to-end HARBOR run. The formulation itself is task-class agnostic: the configuration space, reward correction, acquisition, and safety check apply to any agent harness with a bounded flag space and a reproducible task suite.

Autonomous computational pathology (ACP) converts high-level pathology analysis goals into executable, traceable and clinically bounded workflows. Realizing this capability requires adapting general agentic harness systems to pathology-specific tasks, tools, evidence standards and clinical claim boundaries. We contribute ACP-Bench, a framework that adapts existing harness systems from computational pathology support toward ACP workflow capability. ACP-Bench evaluates 41 pathology workflow tasks, including 24 biomarker, 7 morphology and 10 prognosis tasks spanning 6 body-system groups and 9 endpoint families. The benchmark evaluates 9 models and 3 harness groups (Claude Code, Codex and Open Code), yielding 369 complete trajectories. ACP-Bench evaluates each trajectory across workflow execution, diagnostic performance and clinical-boundary alignment, combining expert-adjudicated process audits, diagnostic assessment and pathologist-validated safety review. Across evaluated systems, workflow initiation, task interpretation and diagnostic reporting were more mature than tool-bound execution, result binding and reflective workflow revision, and formal end-to-end completion remained rare. ACP-Bench provides a reusable standard for auditing whether agentic systems can operationalize pathology workflows before claims of reliable clinical autonomy.

Fast Healthcare Interoperability Resources (FHIR) is the dominant standard for interoperable exchange of healthcare data. In FHIR, electronic health records form a directed graph of resources. Answering clinically meaningful questions over FHIR requires agents to perform multi-step reasoning, filtering, and aggregation across multiple resource types. Prior work shows that even tool-augmented LLM agents (retrieval, code execution, multi-turn planning) often select the wrong resources or violate traversal constraints. We study this problem in the context of FHIR-AgentBench, a benchmark for realistic question answering over real-world hospital data, and frame reasoning on FHIR as a sequential decision-making problem over a queryable structured graph. We implement a multi-turn CodeAct agent and post-train it with reinforcement learning using a custom harness and tools. A LLM Judge provides execution-grounded rewards. Compared to prompt-based, closed-model baselines, RL post-training improves performance while enforcing data-integrity constraints. Empirically, our approach improves answer correctness from 50% (o4-mini) to 77% on FHIR-AgentBench using a smaller and cheaper Qwen3-8B model. We present an end-to-end post-training pipeline (environment building, harness construction, model training and custom evaluation) that reliably improves multi-turn reasoning over structured clinical graphs.

Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make agents hard to train end-to-end with open infrastructure, whose SFT/RL stacks cannot natively express stateful, multi-process harness inference. To address this, we present OpenForgeRL, an open-source framework for training harness-based agents end-to-end in diverse environments. OpenForgeRL achieves this with a lightweight proxy that serves the harness's model calls while recording them as training data for a standard RL codebase (e.g., veRL), and a Kubernetes orchestrator that runs each rollout in its own remote container, together enabling training on any harness in any environment at scale. By decoupling training and inference, OpenForgeRL allows researchers to easily train, study, and improve agents directly in the real harnesses and environments they are deployed with. We validate our framework across diverse, complex harnesses and environments, spanning tool/claw-based agents and multimodal GUI browser- and computer-use agents. Using only hundreds to a few thousand tasks, OpenForgeClaw reaches 31.7 pass^3 and 55.9 pass@3 on ClawEval and 33.7 on QwenClawBench. OpenForgeGUI reaches 37.7 on OSWorld-Verified, 63.0 on Online-Mind2Web, and 72.3 on WebVoyager. Both outperform open baselines of similar size on nearly all benchmarks, and in the GUI setting match or surpass models several times larger. Beyond benchmarks, we analyze how harness choice (e.g., ZeroClaw, OpenClaw, Codex) and RL shape agent behavior. We find that some harnesses are substantially harder to learn than others, and that RL improves agentic reliability, such as self-verification, tool coverage, and completing multi-step plans, though critical abilities such as error recovery remain weak.

Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system. This creates a repair-assignment problem: the same visible failure may call for model post-training, harness engineering, environment redesign, or benchmark repair depending on its source. Because agent behavior emerges from interactions among models, harnesses, users, tools, memory, and environments, outcome-level labels are often insufficient for improvement. Most failure taxonomies do little to resolve this problem because they are benchmark-specific and lack a shared structure. We introduce an interaction-centric taxonomy that localizes failures to the interactions in which they originate and identifies the responsible component. It organizes 41 failure modes by assigning each to an edge between two components and a fault side indicating where the repair belongs. This makes the taxonomy actionable: model-side failures identify targets for post-training, harness-side failures point to scaffolding and tool-integration fixes, and environment or grader failures reveal evaluation conditions requiring redesign. The schema applies across agent architectures, from coding assistants to long-horizon personal assistants and multi-agent systems. We ground the taxonomy in worked examples from public benchmarks, model system cards, published reports, and logged agent trajectories, and evaluate its reproducibility using independent reasoning agents as judges. Across four frontier models, the strongest judge reaches Cohen's κ=0.76 against human category labels, suggesting that the categories capture shared structure rather than annotator-specific preferences.

We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute DSH, collect traces, and judge outcomes. The study covers 14,560 controlled executions over 16 indirect-content channels, text and file carrier modes, 35 payload objectives, one unmodified baseline, and 12 attack methods. The experiment preserves DSH's agent loop, tool registry, model adapter, and session-event path; source tools and sensitive sinks are local fixtures, so attempted actions are recorded without external side effects. We evaluate each trace with a deterministic rule-based judge, (RuleJudge), and a semantic LLM-based judge, (LLMJudge). The strongest observed attack success rates are 17.0% under for fake-completion attack in text mode, 25.5% under for hidden Unicode in file mode, and 16.0% under for the skills channel in file mode. also assigns partial compliance more often than (7.3% versus 2.0%). We relate these results to DSH's treatment of tool results, additional contexts, and tool-call policy hooks, then identify controls that should sit between untrusted content and sensitive actions. Our code is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/Research/deepseek-harness-security-assessment .

LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure. Although external harnesses can substantially improve robustness, harness design remains a manual and expensive process that requires searching over a large space of prompts, tool configurations, and control logic. We propose AutoSaddler, an automatic harness optimization framework that formulates harness improvement as an offline learning problem and iteratively updates the harness using failure signals from mini-batches. AutoSaddler combines failure-trace diagnosis, structured patch generation that treats the harness as code, and validation-based update selection. Experiments on GAIA2, SWE-Bench Pro, and Terminal-Bench 2.0 show that AutoSaddler substantially improves agent performance over the corresponding base harnesses, achieving gains of 9.0, 9.6, and 10.0 percentage points, respectively. Ablation studies further suggest that effective harness optimization benefits from three ingredients: deep debugging rather than shallow reflection, targeted modifications rather than unconstrained editing, and generalization-aware selection rather than trajectory-specific repair. Together, these results suggest that automatic harness optimization is a promising path toward more performant and reliable agent systems.

Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation model. Yet harness design remains manual, task-specific, and fundamentally unscalable. We present JIT-Agent, a harness intelligence model trained to synthesize task-adaptive agent harnesses on the fly for arbitrary off-the-shelf agentic LLMs. We formalize the agent harness as a composable, machine-generatable artifact governed by a fixed four-module protocol, and train JIT-Agent to customize harnesses for a given task at hand, repair harnesses for stable and reliable execution, and self-evolve by distilling performance signals from an expanding archive of prior harness configurations. Equipped with JIT-Agent as a harness helper, DeepSeek-V4-Flash surpasses GPT-5.6 on DeepSearchQA (+9.1) and OdysseyBench (+4.3), while the already strong GLM-5.2 gains up to +20.2 points. Across controlled evaluations, JIT-Agent-generated harnesses are performance-competitive with mature agent runtimes such as OpenCode and Claude Code and consistently improve multi-scale model families of DeepSeek V4, Mimo-V2.5, and Qwen3.6. To our knowledge, JIT-Agent is the first model purpose-built for just-in-time harness generation, establishing harness intelligence as a trainable, transferable, and compounding dimension of agent capability orthogonal to model scaling.

Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness continually evolves as new capabilities are added. We introduce EVOHARNESSBENCH, a benchmark for evaluating agents under controlled harness evolution across three axes (tools, skills, and agents). Unlike existing continual-learning benchmarks for agents, which typically place non-stationarity (i.e., what changes over time) in the task stream while keeping the harness fixed, EVOHARNESSBENCH places non-stationarity in the externally supplied harness itself. It contains 17 multi-stage harness streams constructed deterministically from verifier-based benchmarks, comprising 802 tasks, 520 tools, 42 skills, and 62 agents. We evaluate two complementary settings corresponding to the central challenges of harness evolution: deployment evaluation, which isolates retention of previously accessible competence as the harness expands, and self-evolving adaptation evaluation, which tests whether accumulated experience remains useful as new capabilities are introduced. Our results reveal three persistent gaps. First, harness expansion alone can degrade performance on previously solved tasks, producing harness-induced forgetting. Second, gains from self-evolving adaptation remain inconsistent across stages of harness evolution, capability axes, and environments. Third, retention and adaptation can pull in different directions: preserving earlier competence does not necessarily improve adaptation to newly introduced capabilities, and vice versa. These results establish harness evolution as a distinct challenge for building agents that can keep pace with an evolving harness while preserving previously effective behavior.

Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience. However, generalizable harness RSI remains challenging. First, evolving harnesses on evaluation benchmarks or their subsets makes it difficult to distinguish reusable improvements from benchmark-specific adaptation. Second, single-trajectory updates can conflate systematic harness deficiencies with instance-specific reasoning and solution details, producing modifications that transfer poorly to unseen tasks. Third, localizing recurring behavioral deficiencies within monolithic harnesses is difficult, while whole-harness optimization can entangle unrelated mechanisms and complicate attribution and validation. We propose ModularRSI, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution. ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies. It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection. Each module evolves independently within a restricted modification scope, followed by an integration stage that combines the evolved modules into a unified harness and resolves potential conflicts. To support benchmark-disjoint evolution, we curate 2,000 executable evolution tasks from external sources that are disjoint from downstream evaluation benchmarks. Experiments on TB2.0 and SWE-Bench Verified show consistent improvements on unseen in-domain and cross-domain tasks, with the evolved harness also transferring across different foundation models.

Modern language-model agents are built around the agent loop, where the LLM is placed in an environment exposing a set of tools, and the LLM has full control over the workflow by alternating between tool calls and observing their output. However, certain workflows currently require additional engineering beyond the agent loop itself, such as memory systems and self-improving systems. We built an LLM agent framework, JAZ, to explore the extent to which a minimal harness that is little more than the agent loop itself can accomplish tasks these specialized systems are built for. JAZ exposes a single LLM-based primitive invoke and provides a set of built-in hooks that allow the programmer to apply constraints and monitoring. Generalizing existing code-mode agent loops, invoke is the simplest loop that satisfies two defining properties: (1) the LLM can write arbitrary executable code that can include recursive invoke; (2) everything visible to the LLM --- all inputs to invoke as well as its interaction history with the code environment --- are variables in the code environment. We motivate our design from first principles, viewing invoke as a language primitive representing a function whose implementation is provided at runtime by an LLM every time it is called. To validate the design of our core invoke primitive, we evaluate invoke --- with only prompting, no manually designed tools, harness, or external systems (e.g., memory or the file system) --- on workflows traditionally implemented through specialized external harnesses. On long-horizon workflows requiring recall beyond the context window, JAZ invoke outperforms Letta (MemGPT) by 8\% at half its cost on the recall-heavy portion of StuLife. On continual self-improvement, JAZ invoke outperforms ACE by 4\% at a lower cost on AppWorld.

A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information flow. Because different tasks call for different ways of organizing these operations, the harness needs to be adapted using feedback from the task at hand. We introduce harness learning, which trains a proposer model to revise a solver's harness using execution feedback. We formulate this process as meta-learning over executable programs, with harness revisions playing the role of weight updates in gradient-based adaptation. We train the proposer with reinforcement learning, using the task performance of revised harnesses as the reward. At test time, the proposer uses feedback from successive executions on a new task to refine the harness, without performing any parameter-space update. Experiments on reasoning and multi-hop question answering show that harness learning improves revision quality and that the ability to adapt at test time transfers to unseen tasks. Policies trained on individual revisions can continue improving harnesses over multiple rounds, while the benefits of training on revision sequences vary across settings. These findings suggest a path towards continually learning agents that turn accumulated experience into generalizable improvements.

Mergers play a complex role in galaxy formation and evolution. Continuing to improve our understanding of these systems require ever larger samples, which can be difficult (even impossible) to select from individual surveys. We use the new platform ESA Datalabs to assemble a catalogue of interacting galaxies from the Hubble Space Telescope science archives; this catalogue is larger than previously published catalogues by nearly an order of magnitude. In particular, we apply the Zoobot convolutional neural network directly to the entire public archive of HST F814W images and make probabilistic interaction predictions for 126 million sources from the Hubble Source Catalogue. We employ a combination of automated visual representation and visual analysis to identify a clean sample of 21,926 interacting galaxy systems, mostly with z < 1. Sixty five percent of these systems have no previous references in either the NASA Extragalactic Database or Simbad. In the process of removing contamination, we also discover many other objects of interest, such as gravitational lenses, edge-on protoplanetary disks, and `backlit' overlapping galaxies. We briefly investigate the basic properties of this sample, and we make our catalogue publicly available for use by the community. In addition to providing a new catalogue of scientifically interesting objects imaged by HST, this work also demonstrates the power of the ESA Datalabs tool to facilitate substantial archival analysis without placing a high computational or storage burden on the end user.

The study on GitHub Copilot by GovTech Singapore's Engineering Productivity Programme (EPP) reveals significant potential for AI Code Assistant tools to boost developer productivity and improve application quality in the public sector. Highlighting the substantial benefits for the public sector, the study observed an increased productivity (coding / tasks speed increased by 21-28%), which translates into accelerated development, and quicker go-to-market, with a notable consensus (95%) that the tool increases developer satisfaction. Particularly, junior developers experienced considerable efficiency gains and reduced coding times, illustrating Copilot's capability to enhance job satisfaction by easing routine tasks. This advancement allows for a sharper focus on complex projects, faster learning, and improved code quality. Recognising the strategic importance of these tools, the study recommends the development of an AI Framework to maximise such benefits while cautioning against potential over-reliance without solid foundational programming skills. It also advises public sector developers to classify their code as "Open" to use Gen-AI Coding Assistant tools on the Cloud like GitHub Copilot and to consider self-hosted tools like Codeium or Code Llama for confidential code to leverage technology efficiently within the public sector framework. With up to 8,000 developers, comprising both public officers and vendors developing applications for the public sector and its customers, there is significant potential to enhance productivity.

General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issue-resolution instances across 8 languages and 43 repositories, drawn from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup. We also release Claw-SWE-Bench Lite for faster validation, which is an 80-instance subset selected by a cost-aware, rank-aware procedure over 17 calibration columns. On the full benchmark, OpenClaw with a minimal direct-diff adapter scores only 19.1% Pass@1, whereas the full adapter reaches 73.4% with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw-style harnesses to perform coding tasks effectively. Across an OpenClaw times nine-model sweep and a five-claw times two-model sweep, model choice changes Pass@1 by 29.4 pp and harness choice by 27.4 pp under fixed models; systems with similar accuracy can differ substantially in total API cost. Claw-SWE-Bench therefore treats harness and cost accounting as first-class axes of SWE-style coding-agent evaluation, providing both a full benchmark and a low-cost reference set for reproducible comparison. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.

Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges. Neither captures how an answer was produced. In safety-critical settings, the procedure itself is part of correctness. In this paper, we introduce AgentLTL, a language derived from First-Order Linear Temporal Logic (FO-LTL) that expresses procedural rules over agent traces. It yields a deterministic, judge-free compliance score. In this framework, a single specification drives two usages. The first is harnessing: the constraints score completed traces, or gate tool calls by checking each prefix online, before execution. The second is finetuning: the score serves as a dense reward. On a benchmark spanning ordering, branching, iteration, and grounding, block-and-warn harnessing improves compliance on five of seven models. Finetuning with the same reward yields +38 and +17.5 percentage point gains in accuracy and compliance on held-out patterns, including unseen tool-name aliases. These findings are consistent with the model acquiring procedural structure rather than memorizing surface tool names and procedures.

Modern analyst agents must reason over complex, high token inputs, including dozens of retrieved documents, tool outputs, and time sensitive data. While prior work has produced tool calling benchmarks and examined factuality in knowledge augmented systems, relatively little work studies their intersection: settings where LLMs must integrate large volumes of dynamic, structured and unstructured multi tool outputs. We investigate LLM failure modes in this regime using crypto as a representative high data density domain. We introduce (1) CryptoAnalystBench, an analyst aligned benchmark of 198 production crypto and DeFi queries spanning 11 categories; (2) an agentic harness equipped with relevant crypto and DeFi tools to generate responses across multiple frontier LLMs; and (3) an evaluation pipeline with citation verification and an LLM as a judge rubric spanning four user defined success dimensions: relevance, temporal relevance, depth, and data consistency. Using human annotation, we develop a taxonomy of seven higher order error types that are not reliably captured by factuality checks or LLM based quality scoring. We find that these failures persist even in state of the art systems and can compromise high stakes decisions. Based on this taxonomy, we refine the judge rubric to better capture these errors. While the judge does not align with human annotators on precise scoring across rubric iterations, it reliably identifies critical failure modes, enabling scalable feedback for developers and researchers studying analyst style agents. We release CryptoAnalystBench with annotated queries, the evaluation pipeline, judge rubrics, and the error taxonomy, and outline mitigation strategies and open challenges in evaluating long form, multi tool augmented systems.

The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows. However, current tool-use benchmarks remain misaligned with real-world requirements, relying on AI-generated queries, dummy tools, and limited system-level coordination. To address this, we propose GTA-2, a hierarchical benchmark for General Tool Agents (GTA) spanning atomic tool use and open-ended workflows. Built on real-world authenticity, it leverages real user queries, deployed tools, and multimodal contexts. (i) GTA-Atomic, inherited from our prior GTA benchmark, evaluates short-horizon, closed-ended tool-use precision. (ii) GTA-Workflow introduces long-horizon, open-ended tasks for realistic end-to-end completion. To evaluate open-ended deliverables, we propose a recursive checkpoint-based evaluation mechanism that decomposes objectives into verifiable sub-goals, enabling unified evaluation of both model capabilities and agent execution frameworks (i.e., execution harnesses). Experiments reveal a pronounced capability cliff: while frontier models already struggle on atomic tasks (below 50%), they largely fail on workflows, with top models achieving only 14.39% success. Further analysis shows that checkpoint-guided feedback improves performance, while advanced frameworks such as Manus and OpenClaw substantially enhance workflow completion, highlighting the importance of execution harness design beyond the underlying model capacity. These findings provide guidance for developing reliable personal and professional assistants. Dataset and code will be available at https://github.com/open-compass/GTA.

Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reasoning tasks. However, the underlying mechanism that truly drives performance remains obscured behind intricate system designs. In this paper, we propose HeavySkill, a perspective that views heavy thinking not only as a minimal execution unit in orchestration harness but also as an inner skill internalized within the model's parameters that drives the orchestrator to solve complex tasks. We identify this skill as a two-stage pipeline, i.e., parallel reasoning then summarization, which can operate beneath any agentic harness. We present a systematic empirical study of HeavySkill across diverse domains. Our results show that this inner skill consistently outperforms traditional Best-of-N (BoN) strategies; notably, stronger LLMs can even approach Pass@N performance. Crucially, we demonstrate that the depth and width of heavy thinking, as a learnable skill, can be further scaled via reinforcement learning, offering a promising path toward self-evolving LLMs that internalize complex reasoning without relying on brittle orchestration layers.

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.

Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains difficult and often loses important training signals. We bridge this gap with polar, a rollout framework for scalable asynchronous RL over arbitrary agent harnesses. Polar treats the agent harness as a black box: it proxies LLM API calls, records token-level model interactions, and reconstructs token-faithful trajectories for training. Each rollout node efficiently manages runtime prewarming, agent execution, trajectory reconstruction, and evaluation in parallel, exposing asynchronous service endpoints that can be consumed by independent trainers at scale. This decoupled design makes Polar agnostic to agent harnesses, training infrastructure, and RL algorithms while improving compute utilization for long-running agent workloads. We validate polar by training agents on software-engineering tasks with popular coding harnesses. Using simple GRPO, polar improves Qwen3.5-4B by 22.6, 4.8, 0.6 and 6.2 points on SWE-Bench Verified with the Codex, Claude Code, Qwen Code and Pi harnesses, respectively. We further demonstrate Polar for offline data generation over custom harnesses and ablate trajectory reconstruction strategies. Polar rewrites its preceding work, Prorl Agent, and has been registered as one of NeMo Gym environments.

The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time. This limits adaptation when the test distribution, failure modes, or tool interactions differ from those seen during development. We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs. We introduce Test-Time Harness Evolution (TTHE), which treats the executable harness as the state of test-time adaptation. During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces, without gold labels or task-specific supervision; a judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs. Crucially, TTHE does not update model weights, require gold labels, or train a separate adaptation model: solver, proposers, and judge are different roles and harnesses around the same frozen LLM, so all adaptation occurs through changes to the surrounding program. Across text-to-SQL, competitive programming, software engineering, data-science coding, and agentic tool-use tasks, TTHE improves fixed ReAct-style baseline harnesses, yielding persistent, inspectable improvements rather than a pre-searched workflow or per-query retries. These results recast test-time adaptation for LLM agents as evolution over executable control programs and identify execution-derived proxy reliability as a central challenge for robust unsupervised agent improvement.

Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification. At the same time, frontier and open models are becoming structurally specialized: a model that is strong at code editing, long-context recovery, tool use, mathematical reasoning, or low-latency response may not dominate on the other axes. This makes model selection inside an agent a core systems problem rather than a per-query serving trick. Existing routing methods mostly optimize single-turn cost-quality trade-offs and therefore miss the execution state, intermediate failures, and feedback loops that make agents different from chat completion. We propose Harness-Native agentic routing, a step-level routing paradigm that selects either a single best-fit model for cost-effective execution or multiple complementary models for ensemble-style accuracy improvement, conditioned on the full harness state. The key insight is that every routing decision naturally produces a structured data record -- consisting of the query, harness state, model choice or model set, execution trace, outcome, and cost -- whose labels are supplied by the environment rather than by the router itself. These records form a harness-native data flywheel: execution traces train better routers and harness-native models, which improve cost-quality trade-offs and generate more traces under the same budget. We instantiate this idea in OpenSquilla with a four-layer routing stack, an open LightGBM cold-start ranker, and a staged router-model path that turns logged arena records into progressively stronger routing policies. The report studies singleton and multi-model routing on agentic benchmarks including DRACO and PinchBench, and argues that agentic routing is not merely cost control, but a data engine for agent-native training.

Tool-calling benchmarks are increasingly used to rank language-model agents, yet their scores are often treated as ground truth without validating the evaluators themselves. We present a systematic validity and reproducibility audit of four major tool-calling benchmark families: BFCL v4, τ2-Bench, LiveMCPBench, and MCP-Atlas. Across 496 expert-reviewed benchmark tasks, we find 92 evaluator-human disagreements, corresponding to an 18.5% misalignment rate. The failures are not isolated annotation mistakes: deterministic benchmarks exhibit brittle state matching, trajectory lock-in, incorrect ground truths, substring-based communication failures, and reward-basis misalignment, while LLM-judge benchmarks exhibit rubric drift, hallucinated completion, answer-only scoring, and substantial run-to-run variance. In LiveMCPBench, 23 repeated evaluations of the same setup produce scores ranging from 57.9% to 76.8%, a spread of 18.9 percentage points, large enough to change leaderboard conclusions. These results show that current tool-calling scores can reflect evaluator artifacts rather than agent capability. We introduce a unified taxonomy of tool-calling evaluation failures, release trace-level audit artifacts and corrected evaluation components, and argue for decomposed metrics that separately measure tool invocation, task completion, and outcome verification. Our findings suggest that progress in tool-using agents requires benchmarks whose evaluators are themselves reproducible, auditable, and aligned with human judgments of task success. We further introduce Tool-Veritas, a configurable benchmark that combines deterministic state verification with optional qualitative judging, and Harness Lab, an open-source system for benchmark execution, trace inspection, repeated-run comparison, and evaluator debugging.

The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control. Existing safety mechanisms often treat the harness as a fixed deployment artifact, limiting their ability to evolve with emerging risks. Moreover, coupled functions across harness components obscure safety responsibility attribution, making localized evolution difficult. We propose Safety Harness Evolution (SHE), a framework that learns evolving safe boundaries from rollout trajectories. SHE decomposes the harness into four artifacts with explicit safety responsibilities, including the System Prompt, Rule Bank, Safety Memory, and Tool Policy, defining clear functional boundaries for localized evolution. Based on this decomposition, SHE introduces an attribution-guided evolution loop that converts trajectory failures into structured diagnoses, learns artifact-specific boundary refinements, and selects evolved harnesses through safety-utility validation. Experiments on Agent-SafetyBench demonstrate that SHE effectively enhances safety through harness evolution, achieving a 3.1x ASR reduction compared with static SafeHarness, while also improving benign utility. The evolved harness further generalizes to unseen risks on the held-out AgentHarm benchmark and transfers across agent models without additional evolution.

Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing stays strong when the setting changes. We evaluate 66 configurations: four configurable harnesses (OpenHands, DeepSeek Harness, PI, and openJiuwen) paired with five models on TUA-Bench, ALE-CLI, and Terminal-Bench 4, plus the native Codex-GPT and Claude Code-Claude pairings. Model rankings reverse across harnesses. On Terminal-Bench 4, Claude leads GPT by 7.94 points in OpenHands but trails it by 30.16 points in PI. For four of the five models, the best harness changes from one benchmark to another, yet some pairings hold: openJiuwen gives Kimi its highest score on all three benchmarks, by 5.61 to 11.11 points. A model's own vendor harness is not reliably its best, and higher cost does not reliably buy a higher score. On Terminal-Bench 4, GPT scores higher under PI than under DSH at less than a quarter of the cost per task. Matched trajectories suggest why fit varies. Models start almost all repairs themselves, so much depends on whether the harness hands failures back in a form the model can use. GPT does best with PI's lean scaffold, while Kimi, which often issues malformed tool calls, does best in openJiuwen. We argue that the model, the harness, and the task should be evaluated together, and we release the harness adapters, evaluation code, and all 6,204 scored trajectories at https://github.com/liyix/finding-the-right-fit and https://huggingface.co/datasets/yixuanli97/finding-the-right-fit.

Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component of a broader agentic interaction system comprising the environment, task, agent harness, and evaluator. Scaling environments in isolation, however, does not guarantee commensurate gains in model performance, because reliable learning signals depend on coherent interactions among all components of the agentic interaction system. To address this problem, we introduce WEFT (Whole-system Evolution For Tool-use Post-training), which couples scalable agentic interaction system construction, execution-driven self-evolution, and stable post-training. WEFT scales agentic interaction system construction across environment breadth, task complexity, and interaction diversity. Execution-driven self-evolution iteratively uses execution traces and state evidence to attribute failures and revise the responsible components, with fresh rollouts evaluating the changes and providing evidence for subsequent evolution rounds. For stable post-training at scale, WEFT addresses both optimization and execution reliability: prefix-preserving sampling retains verified progress and atomic-turn credit assignment localizes learning signals, while MegaMCP maintains isolated, recoverable state across concurrent rollouts over shared tool services. Extensive experiments across various models and benchmarks demonstrate the effectiveness of WEFT for tool-use post-training. WEFT-8B and WEFT-14B outperform all evaluated matched-size environment-scaling baselines on BFCL V4, τ^2-Bench, and Claw-Eval. In particular, WEFT-14B improves over Agent-World-14B by 6.41, 2.23, and 12.27 percentage points. WEFT-35B-A3B further extends these gains to more challenging long-horizon workflow benchmarks, including Toolathlon-Verified and AutomationBench.

In this work, we explore MammoClaw, a training-free agent framework that leverages frozen MLLMs for mammography analysis. To support agentic investigation, we equip the agent with lightweight mammography-specific tools for targeted image analysis, including ROI, paired-view, and contralateral-breast examination. MammoClaw iteratively gathers evidence through these tools, while skill evolution enables non-parametric adaptation by transforming failed trajectories into reusable guidance for later runs. We evaluate the framework on BI-RADS assessment and breast density estimation tasks. In our experiments, we find that tools alone do not reliably improve performance, whereas evolved skills can improve tool-use behavior and performance in some settings. Beyond these results, MammoClaw enables transparent inspection of evidence acquisition, tool interactions, and failure modes, facilitating the analysis and auditing of agent behavior. We view this work as an exploratory study of training-free, self-evolving agentic approaches for mammography and hope it provides a concrete starting point for future work on mammography-specific tools and self-evolution mechanisms. We release our code at https://krishnakanthnakka.github.io/mammoclaw.

Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software. This study tested that assumption directly. Ninety independent agent runs built the same application, a real time retrospective board, from one detailed specification, each scored on a fixed 14 criterion functional rubric (42 point maximum) and a visual quality review. The runs spanned several model generations, two agent harnesses, two reasoning effort levels, a testing tool, and two design oriented prompts. Capability tier dominated: frontier models clustered near the ceiling while a low cost local model fell to 24 to 37 points. A criterion level analysis revealed what run totals conceal. Container deployment was the dominant defect, failing first try in 44 percent of runs, with its failure rate shifting sharply across model generations while mean totals moved less than a point. The testing tool raised cost by 42 to 68 percent without improving functional score or reliability, even on interface visible criteria. Raising reasoning effort from High to xHigh lifted first try perfect runs from 28 percent to 89 percent and cut corrective prompts about five fold, for 9 to 29 percent more cost. A design oriented prompt raised visual quality, 4.5 versus 3.0 on a 5 point scale, without lifting function, and a one paragraph paraphrase of its directive reproduced the entire lift. The practical lesson is to match the fix to the failure: most first run failures came from weak reasoning, which a stronger model or more effort prevents, not from visible flaws a checking tool would catch.

We present Test-Driven AI Agent Definition (TDAD), a methodology that treats agent prompts as compiled artifacts: engineers provide behavioral specifications, a coding agent converts them into executable tests, and a second coding agent iteratively refines the prompt until tests pass. Deploying tool-using LLM agents in production requires measurable behavioral compliance that current development practices cannot provide. Small prompt changes cause silent regressions, tool misuse goes undetected, and policy violations emerge only after deployment. To mitigate specification gaming, TDAD introduces three mechanisms: (1) visible/hidden test splits that withhold evaluation tests during compilation, (2) semantic mutation testing via a post-compilation agent that generates plausible faulty prompt variants, with the harness measuring whether the test suite detects them, and (3) spec evolution scenarios that quantify regression safety when requirements change. We evaluate TDAD on SpecSuite-Core, a benchmark of four deeply-specified agents spanning policy compliance, grounded analytics, runbook adherence, and deterministic enforcement. Across 24 independent trials, TDAD achieves 92% v1 compilation success with 97% mean hidden pass rate; evolved specifications compile at 58%, with most failed runs passing all visible tests except 1-2, and show 86-100% mutation scores, 78% v2 hidden pass rate, and 97% regression safety scores. The implementation is available as an open benchmark at https://github.com/f-labs-io/tdad-paper-code.

Financial AI agents often fail for a simple reason: they make users carry the complexity. A user must repeatedly restate goals, risk preferences, portfolio context, past judgments, and shifting market assumptions, while the agent answers, retrieves, acts, and forgets. In finance, this is not just inconvenient. In tasks such as market analysis, copy-trading review, and trade preparation, forgotten context and stale memory can create latency, repeated errors, weak auditability, and unsafe decisions. We propose the interaction-native knowledge harness (InKH), an architecture for financial LLM agents that absorbs complexity into the system. InKH converts user, market, portfolio, and tool events into structured operational knowledge. It uses passive knowledge injection to assemble a bounded working context buffer before the main model step, temporal graph memory for low-latency retrieval, a wiki audit surface for human-readable governance, and background extraction with maturity, decay, and write-time invalidation. We evaluate InKH on a reproducible controlled synthetic benchmark with 24 random seeds, 4 rounds, 80 episodes per round, and 6 baselines, producing 46,080 baseline-conditioned evaluations. InKH achieves mean task quality of 0.815 at 900 ms latency. Compared with agent-driven wiki-walk memory, it reduces latency by 82.95 percent, token cost by 82.29 percent, and stale-knowledge usage by 96.58 percent, while improving quality by 0.108 and traceability by 0.461. Compared with a temporal-graph system without invalidation, it improves quality by 0.050 and reduces stale-memory usage by 96.58 percent with comparable serving cost. The results support a design thesis for financial AI: adoption happens when complexity is absorbed by the system rather than transferred to the user. The benchmark validates architecture-level behavior, not live trading performance.

LLM agents increasingly rely on agent harness: the runtime infrastructure around the base model that defines execution environments, tool interfaces, context, lifecycle orchestration, observability, verification, and governance. Existing self-improving agents and automatic harness evolution methods mainly improve agents through runtime supervision, prompt optimization, workflow search, or harness modification based on final outcomes. However, they often fail to diagnose where the responsible evidence lies in failed trajectories and which harness implementation mechanism causes the unreliable behavior, resulting in broad, indirect, or poorly scoped changes. This paper proposes HarnessFix, a trace-grounded and diagnosis-driven framework for repairing agent harnesses. HarnessFix compiles raw execution traces and harness artifacts into a Harness-aware Trace Intermediate Representation (HTIR), which normalizes fragmented trajectory evidence, captures step-level data-flow and control-flow relations, and aligns runtime steps with the harness artifacts that shape their behavior. It then attributes failures to responsible steps and harness artifacts, and consolidates recurring diagnoses into repair-oriented flaw records. Finally, HarnessFix maps these records to scoped repair operators, generates patches under flaw-specific repair specifications, and accepts them through regression-aware validation. We evaluate HarnessFix on four popular benchmarks, and results show that it improves the performance over the initial harnesses by 6.3% to 18.4%, significantly outperforming human-designed and self-evolution baselines. HarnessFix highlights the value of treating failed trajectories not only as feedback signals, but also as structured evidence for diagnosing and repairing the harness mechanisms behind agent failures.

This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer that governs context construction, tool interaction, orchestration, and verification around a language model, is often a stronger determinant of agent performance than the model it wraps. We formalize and defend the Binding Constraint Thesis: in this regime, performance variance is governed more by harness configuration than by model choice, and current evaluation protocols therefore systematically misattribute harness-level gains to model improvements. We support this thesis along three lines. First, a control-theoretic formalization treats the harness as the controller of a closed-loop dynamical system and the LLM as the stochastic policy it governs, which explains why small harness changes can produce performance shifts that exceed those obtained by substituting one model for another. Second, published benchmarks, industry deployments, and a controlled variance decomposition show that harness-induced variance can substantially exceed model-induced variance, including cases of model ranking reversal. Third, we propose a harness-aware evaluation framework with a disclosure standard and a variance decomposition protocol. Until harness specifications are disclosed, leaderboard comparisons for long-horizon agents should be treated as incomplete and potentially misleading.

Figural divergent thinking is the ability to develop a given shape fragment into an original drawing. In humans, this ability is assessed with incomplete-drawing tasks. We introduce PainterBench, a benchmark that ports the incomplete-drawing task to the agentic setting. The agent draws on a canvas through tool calls and observes the result after every turn. The canvas includes a starting shape which cannot be erased, and the agent's goal is to incorporate this shape into the most original drawing it can produce. The task is open-ended, and the agent itself decides when the drawing is finished. The benchmark tests incremental visual planning over a short horizon and the transfer of creative ability from pretraining to multi-turn tool use. We evaluate 14 multimodal language models from small to frontier scale. Across the primary study and six sensitivity analyses, we collect 2,700 drawings and crowdsource creativity and recognizability ratings for every drawing and for 300 human reference drawings. We also present ViDrA-adapted, an automated scorer that predicts human creativity ratings of agent drawings (r = 0.85 on random held-out test split). Figural divergent thinking varies widely across the 14 models, and GPT-6 Astra produces the most creative drawings. Relative to the human drawings, the agent drawings score higher in creativity but lower in recognizability. We release the final drawings, per-round canvas snapshots, tool call traces, stimulus bank, benchmark harness, crowdsourced ratings (N = 72,000), and ViDrA checkpoint.

Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities but potentially incurring substantial costs. Moreover, tool use is not always beneficial: redundant or low-utility calls can even harm task performance. Effective tool use, therefore, hinges on a core LLM decision: whether to call or not call a tool when performing a task. We introduce a principled framework inspired by decision-making theory to understand tool-use decisions along three key factors: necessity, utility, and affordability. Our analysis combines two complementary lenses: a normative perspective that infers true need and utility for optimal tool calls, and a descriptive perspective that infers the model's self-perceived need and utility from their observed behaviors. We evaluate six open models and a proprietary OpenAI model across native and customized harnesses, two tools, and six tasks. Models' perceived need and utility remain misaligned with their true values, particularly under budget constraints. This misalignment produces both costly overuse and performance-degrading calls. To improve the tool decisions, we train lightweight latent estimators of need (LNEs) from model hidden states. LNEs generally predict true need more accurately than model self-reports and improve budgeted tool allocation across model scales and tool types. Code and dataset available at https://github.com/QinyuanWu0710/ToCall_or_NotToCall.

Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before producing a final result. Existing benchmarks, however, often evaluate tool use, computer use, and multimodal reasoning in isolation, leaving a gap between benchmark settings and end-to-end omni-modal tool use in the real world. To address this gap, we introduce MM-ToolBench, a benchmark and evaluation harness for task-oriented omni-modal tool use. MM-ToolBench contains 100 executable tasks from two macro task families, Customer Service and Intelligent Creation, covering 20 subcategory slices and supported by 27 MCP servers with 324 tools. The central design of MM-ToolBench is closed-loop multimodal verification: agents must execute tools, inspect rendered or transformed artifacts, and self-correct when outputs fail task-specific requirements. To make such evaluation scalable and verifiable, MM-ToolBench couples MCP-based execution with task-specific grounded evaluators and a semi-automated construction pipeline for scenario discovery, task instantiation, evaluator synthesis, and human audit. Experiments on 15 contemporary agentic models show that MM-ToolBench remains highly challenging: Claude Opus 4.6, commonly regarded as one of the strongest coding-agent models, achieves only 32.0% task success, far below the 94.0% human benchmark. We envision MM-ToolBench as a practical foundation for evaluating and advancing next-generation omni-modal tool-using agents through closed-loop multimodal verification.

Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without deterministic ground truth and the need to interleave textual arguments with visual evidence. We propose Ptah, a multi-agent harness for interleaved report generation. Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages, where specialized agents construct visual-aware plans, collect claim-grounded evidence, maintain source-aligned images in a Visual Working Memory, and compose reports through declarative multimodal tool use. A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow. We further introduce PtahEval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that Ptah produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines.

This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the harness: treating the structured execution layer around a foundation model as a first-class object of design, evaluation, and optimization. Although recent large language models enable agents to use tools, retrieve information, maintain memory, and execute long-horizon workflows, evaluation remains largely model-centric, often reducing agents to final-task success while treating memory, retrieval, tool use, orchestration, verification, and governance as secondary implementation details. This framing is increasingly inadequate because agent performance emerges from the interaction among the foundation model, memory substrate, context constructor, skill-routing layer, orchestration loop, and verification-and-governance layer. Together, these components form the agent harness, which translates model capability into long-horizon agent behavior. We study scaling the harness through three core bottlenecks: context governance, trustworthy memory, and dynamic skill routing, together with the orchestration and governance mechanisms that coordinate and constrain them. We further outline a research agenda for harness-level benchmarks that go beyond one-shot task success to measure trajectory quality, memory hygiene, context efficiency, communication fidelity, verification cost, and safe evolution over time. To make the discussion concrete, we develop CheetahClaws: https://github.com/SafeRL-Lab/cheetahclaws, a Python-native reference harness, and compare it with Claude Code and OpenClaw. Our main claim is that future progress in agentic AI will depend as much on system design as on stronger foundation models.

A coding agent combines a model with a harness, which decides what the model sees, which tools it can use, and how the work continues. We ask whether changing the harness changes the result when the model and task stay fixed. We compare two configurations of the same harness on three coding benchmarks. The control supplies the full conversation in time order, while the treatment keeps the same record but mechanically shortens older tool results as the context fills and responds to repeated or stalled work. Under tight context, the treatment raises mean per-task fail-to-pass fraction (F2PF) in all three pressure comparisons and increases complete solutions on SWE-bench Verified and SWE-bench Pro. The tight-window Verified comparison uses 169 tasks, a 20,480-token window, and a fixed 480-second attempt endpoint; on this cohort, treatment raises mean per-task F2PF from 28 percent to 49 percent and complete solutions from 43 to 72. Without model-specific retuning, the same frozen treatment also raises both endpoints on the same cohort for three additional models with different designs. In the wide-window Qwen3.6 comparisons, observed arm outcomes are close on Verified and Pro, while FeatureBench retains a higher mean per-task F2PF under treatment. On the wide-window Verified cohort, treatment also serves fewer prompt tokens per turn. Because changing the harness changed what unchanged model weights could accomplish, coding-agent evaluations should treat the model and harness together as the tested solver.

As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback. Token efficiency therefore becomes important for scaling recursive self-improvement. We take an RSI-inspired approach at the harness layer, scaling auto-research loops across increasingly numerous and diverse environments for harness rollouts. At this scale, the process yields reusable improvements that transfer beyond their development setting, moving automated harness discovery toward production-level outcomes. Four mechanisms survive selection and form SoL-Pi, spanning action execution, context compaction, observation handling, and delegated reading. On the 51-task EdgeBench evaluation, SoL-Pi achieves performance comparable to Pi across GPT-5.6 Sol and Opus 5 while reducing recorded token traffic by 44.7-49.0% and API cost by about one third. In other words, estimated hourly savings are \8.75-13.50 relative to native Codex and Claude Code harnesses, and \4.36-5.71 relative to Pi.

The landscape of AI coding assistance is undergoing a fundamental shift from complex IDE plugins to versatile, terminal-native agents. Operating directly where developers manage source control, execute builds, and deploy environments, CLI-based agents offer unprecedented autonomy for long-horizon development tasks. In this paper, we present OPENDEV, an open-source, command-line coding agent engineered specifically for this new paradigm. Effective autonomous assistance requires strict safety controls and highly efficient context management to prevent context bloat and reasoning degradation. OPENDEV overcomes these challenges through a compound AI system architecture with workload-specialized model routing, a dual-agent architecture separating planning from execution, lazy tool discovery, and adaptive context compaction that progressively reduces older observations. Furthermore, it employs an automated memory system to accumulate project-specific knowledge across sessions and counteracts instruction fade-out through event-driven system reminders. By enforcing explicit reasoning phases and prioritizing context efficiency, OPENDEV provides a secure, extensible foundation for terminal-first AI assistance, offering a blueprint for robust autonomous software engineering.

LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly update model parameters, many failures in deterministic, rule-governed domains stem from mismatches at the model--environment interface. We propose Life-Harness, a lifecycle-aware runtime harness that improves frozen LLM agents without changing model weights or evaluation environments. Life-Harness evolves from training trajectories by converting recurring interaction failures into reusable interventions across environment contracts, procedural skills, action realization, and trajectory regulation, and remains fixed during held-out evaluation. On seven deterministic environments from τ-bench, τ^2-bench, and AgentBench, Life-Harness improves 116 out of 126 model--environment settings across 18 model backbones, with an average relative improvement of 88.5%. Harnesses evolved only from Qwen3-4B-Instruct trajectories transfer to 17 other models, showing that Life-Harness captures reusable environment-side structure rather than model-specific behavior. These results position runtime interface adaptation as a complementary alternative to model-centric agent training. Code is available at GitHub.

Agentic coding tools present new opportunities to transform research workflows. The performance of agent systems built depends on both large language models (LLMs) and the harness around LLMs, which is the orchestration code that determines an agent's behavior. We present ToFu, an agentic harness for researchers that reads your codebase, edits files, runs commands, and integrates with your development tools. ToFu plays a dual role in research. As a research assistant, it supports practical research workflows with superior token efficiency, lower cost, and multilingual capability compared with existing agentic harnesses. Its release under the MIT License further enables local deployment for privacy-sensitive users. As a research object, ToFu provides a white-box agentic harness that allows researchers to inspect, modify, and evaluate its orchestration logic, tool-use behavior, and harness design, while retaining strong benchmark performance and an application-level user experience.

LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tuned to a single scenario (multi-session chat or a single trajectory format), and there is little evidence that they generalize across the heterogeneous trajectories agents encounter in deployment. We revisit eight memory systems plus an agentic harness for search problems, on five scenarios: single-turn QA, multi-session chat, agentic-trajectory QA, memory stress tests, and long-horizon agentic tasks. The harness, which self-manages flat text-file storage via tool calls, achieves the best cross-task ranking, suggesting that memory performance hinges on giving the agent active control over storage and retrieval rather than on a passive store behind a fixed pipeline. We instantiate this insight in AutoMEM, an agentic memory harness with a self-managed tool interface that achieves the best cross-scenario generality among the systems we evaluate.

Context engineering has become central to building reliable AI agents, yet it remains largely unmeasured. Agents do not fail in isolation: their behavior is shaped by the instructions, tools, memory, retrieved knowledge, guardrails, and untrusted inputs accumulated in their context. When this context is weak, agents drift, hallucinate, misuse tools, ignore constraints, become vulnerable to injection, and waste tokens. This paper validates context-engineering quality as an independent leading indicator of agent reliability. We implement the measurement in ProofAgent-Harness, an open-source infrastructure for AI agent evaluation that uses multi-juror, consensus-based scoring. The harness assesses context across seven criteria: role clarity, guardrail coverage, instruction consistency, tool schema quality, grounding sufficiency, injection hardening, and token efficiency. Crucially, the context score is isolated from behavioral metrics and release decisions, enabling a non-circular validation. Through a controlled context-quality study across regulated agent domains, holding frontier LLM agents fixed and varying only their operating context, we show that context-quality criteria consistently predict their corresponding behavioral outcomes. Grounding sufficiency predicts hallucination resistance, guardrail coverage predicts manipulation resistance, instruction consistency predicts instruction following, and tool-schema quality predicts tool use. These findings establish context measurement as a validated preflight signal for agent reliability and position context engineering as an auditable layer of agent evaluation and governance.

Real-time proactive agentic system, capable of modeling Human State of Mind, using foundation EXG model and text embeddings model, running fully offline on the edge. Unlike all previously known systems, the NeuroSkill(tm) system leverages SKILL.md description of Human's State of Mind via API and CLI provided by the system, directly from the Brain-Computer Interface (BCI) devices, which records Human biophysical and brain signals. Our custom harness - NeuroLoop(tm) - utilizes all of the above to run agentic flow that manages to engage with the Human on multiple cognitive and affective levels of their State of Mind (e.g., empathy), by providing actionable tool calls and protocol execution with explicit or implicit requests from the Human. GPLv3 open-source software with ethically aligned AI100 licensing for the skill markdown.

Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is still measured by grading answers. We introduce AgentFairBench, a cheap, reproducible, multi-domain benchmark for demographic disparity in the actions of LLM agents. Grounded in a companion framework, the Bias Conduction Framework (BCF, restated here), it spans three regulator-anchored domains: hiring, lending, and medical triage. Synthetic, demographic-neutral profiles are evaluated in counterfactual matched sets that vary only a name-coded race x gender signal (in the Bertrand Mullainathan tradition), under four agent scaffolds of increasing agency (direct, chain-of-thought, multi-agent deliberation, tool-augmented). A NumPy-only harness computes counterfactual flip rate, mean absolute score difference (MASD), action-rate disparity, and tool-invocation disparity, with bootstrap confidence intervals, paired tests, and false-discovery-rate control, for single-digit dollars per model. A live leaderboard with a held-out private split and a contamination canary admits external models by submission. Our pilot (864 decisions plus a test-retest replication) carries a methodological lesson: comparing a six-group score spread against a two-run noise difference overstates disparity by ~ 2.4X through statistic arity alone. Against an arity matched noise floor and an omnibus group test, claude haiku 4 5 shows no demographic effect above sampling noise (0 of 120 pairwise and 0 of 9 omnibus contrasts survive correction); a planted-bias test confirms the instrument detects disparity when present. The contribution is a sound, sensitive, adoption-ready instrument, the arity matched null methodology, and open artifacts to scale it. Code, data, and harness are released under open licenses, with an anonymized review artifact.

Video production workflows offer a rich and demanding arena for evaluating multimodal AI agents: they require composite capabilities across text, image, audio, and video understanding, along with long-horizon planning, and tool use. To this end, we introduce AgenticVBench, a benchmark of 100 agentic tasks across 4 task families spanning the real world post-production workflow, constructed from real production workflows contributed by 20 industry experts averaging 6 years of professional experience. Tasks are paired with evaluation specifications that combine programmatic verifiers and expert rubrics. We evaluate frontier vision-language models (VLMs) with both vendor-native and open-source harnesses. The best evaluated agent stack barely crosses 30%, far below human expert performance on the same tasks. We further find that the choice of harness substantially affects model behavior, including scores, tool-use patterns, and failure modes. AgenticVBench provides a foundation for diagnosing and improving both models and harnesses for agentic video production. Benchmark website: https://agenticvbench.com.

We employ a tool-interacting divide-and-conquer strategy enabling large language models (LLMs) to answer complex multimodal multi-hop questions. In particular, we harness the power of large language models to divide a given multimodal multi-hop question into unimodal single-hop sub-questions to be answered by the appropriate tool from a predefined set of tools. After all corresponding tools provide the LLM with their answers, the LLM generates the next relevant unimodal single-hop question. To increase the reasoning ability of LLMs, we prompt chatGPT to generate a tool-interacting divide-and-conquer dataset. This dataset is then used to efficiently finetune the corresponding LLM. To assess the effectiveness of this approach, we conduct an evaluation on two recently introduced complex question-answering datasets. The experimental analysis demonstrate substantial improvements over existing state-of-the-art solutions, indicating the efficacy and generality of our strategy

Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework that synthesizes a corpus into a hierarchical, typed, navigable wiki and trains an agent, WikiResearcher-9B, to retrieve information through multi-turn tool use. The wiki organizes knowledge into three layers - document overviews, cross- document topic pages, and page-level source records; enabling progressive refinement of retrieval when initial lookup misses. We optimize the agent's navigation policy with on-policy reinforcement learning with a multi-component reward function balancing answer correctness, retrieval quality and trajectory efficiency. Evaluation on ViDoRe-V3 (8 domains), FinanceBench, and memory benchmarks (LoCoMo, LongMemEval, PersonaMem-v2) shows that WikiResearcher- 9B which is our RL-tuned Qwen 9B model, significantly outperforms same-size untrained baselines and exceeds or matches larger external models. SearchWiki paired with WikiResearcher-9B demonstrates that learned navigation over structured corpora is a superior alternative to flat retrieval.

Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories. Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls, and runs inside a reproducible Docker container hosting an actual CLI agent harness (OpenClaw, Claude Code, Codex, or Hermes Agent) with access to real tools rather than mock services. Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification. Across 19 frontier models, the best, Claude Opus 4.7, reaches only 62.2% overall under OpenClaw, while every other model stays below 60%, and switching harness alone shifts a single model by up to 18 points. These results show that long-horizon, native-runtime agent evaluation remains a far-from-resolved task for current frontier models. We release the tasks, code, and containerized tooling to support reproducible evaluation.

Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop. Existing evaluations often reduce this process to isolated task scores or a single sequential curve, obscuring whether an update produces reusable improvement, overfits recent tasks, increases cost, or harms older behavior. We introduce SEAGym, an evaluation environment for measuring agent harness updates across training, validation, test, replay, and cost records. SEAGym turns Harbor-compatible benchmarks into dynamic self-evolution task sources with train batches, frozen update-validation, held-out ID and OOD transfer views, replay diagnostics, and saved snapshot and metric records. Instantiating SEAGym on Terminal-Bench 2.0 and HLE, we compare ACE, TF-GRPO, and AHE under a shared epoch/batch protocol. The results show that these evaluation views provide complementary signals about the evolution process: frequent updates may fail to improve held-out performance, useful intermediate snapshots may collapse later, and source diversity and model backend can affect harness reliability.

The generative capabilities of Large Language Models (LLMs) are rapidly expanding from static code to dynamic, interactive visual artifacts. This progress is bottlenecked by a critical evaluation gap: established benchmarks focus on algorithmic correctness and are blind to the visual fidelity and interactive integrity that define modern user experiences. To bridge this gap, we introduce ArtifactsBench, a new benchmark and paradigm for the automated, multimodal evaluation of visual code generation. Our framework programmatically renders each generated artifact and captures its dynamic behavior through temporal screenshots. This visual evidence, alongside the source code, is then assessed by a Multimodal LLM (MLLM)-as-Judge, which is rigorously guided by a fine-grained, per-task checklist to ensure holistic and reproducible scoring. We construct a new benchmark of 1,825 diverse tasks and evaluate over 30 leading LLMs. Our automated evaluation achieves a striking 94.4% ranking consistency with WebDev Arena, the gold-standard for human preference in web development, and over 90% pairwise agreement with human experts. This establishes ArtifactsBench as the first framework to reliably automate the assessment of human-perceived quality at scale. Our analysis provides a high-resolution map of the current SOTA, revealing that generalist models often outperform domain-specific ones. We open-source ArtifactsBench, including the benchmark, evaluation harness, and baseline results at https://artifactsbenchmark.github.io/, to provide the community with a scalable and accurate tool to accelerate the development of user-centric generative models.

Long-horizon LLM agents accumulate tool results, files, plans, and user constraints that are too structured to be treated as a disposable text suffix. Current systems mostly rely on in-run heuristics such as chronological pruning and tool-output masking, or on final self-summary near a context limit. Heuristics are cheap but blind to future dependencies; summaries preserve narrative state but often hide exact evidence, locators, and editable artifacts. We present Self-GC, where GC denotes self-governing context while deliberately echoing garbage collection: the system does not merely reclaim unused tokens, but governs the lifecycle of agent context objects. Self-GC turns user turns, tool spans, and skill state into indexed objects; asks a side-channel planner to propose fold, mask, and prune actions; and lets the harness enforce recoverable sidecars, safe commit boundaries, and cache-aware commit. On a 33-session Hard Set, Self-GC prunes 43.95% of prefix tokens while leaving 84.85% of future continuations unaffected, compared with no-impact rates of 54.55% to 69.70% for heuristic baselines. On a 332-session production-derived suite, three planner backbones reach no-impact rates of 91.27% to 94.58%, while baselines remain at 77.71% to 87.46%. In production, an online account-level split reduces daytime average input tokens by 10% to 15%, with peak reductions near 20%. These results point to context management as runtime lifecycle control over indexed, recoverable objects rather than post hoc text cleanup.

Autonomous software generation (ASG) aims to turn human requirements into executable applications, but delivering these applications does not necessarily establish that their interacting components satisfy the specified behavioral requirements. We introduce GameASG-Bench, a benchmark that makes behavioral testability part of the generation task for game development. Our design declares an evaluation interface specification before generation, fixing legal starting scenarios, player-level actions, stable snapshots, rejection behavior, and invariants while leaving private implementations open. Concretely, we include: (i) static L1 checks that assess source-level compliance; and (ii) browser-executed L2 checks that combine semantic observations with real input and runtime evidence. We implement this protocol as 47 browser-native game-generation tasks spanning 12 primary genres and both 2D and 3D interaction, each with executable checks and an independently verified reference implementation. Our experiments answer four key questions about end-to-end agent performance, tool access and nominal turn budget, reasoning effort, and harness choice. Across nine agent stacks, the highest observed mean L2 check pass rate is 93.2%, yet the highest observed strict task success rate, requiring all L1 and applicable L2 prerequisite and core requirement checks, is only 55.3% (26/47 tasks). For DeepSeek-V4-Flash, full tool access and larger nominal turn budgets yield more strict task successes, while the strict task success rate is not monotonic in reasoning effort. Both tested harnesses achieve 18 strict task successes, but only ten tasks succeed under both. These results expose task-level compliance gaps that high average check pass rates actually obscure.

LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally static in enterprise deployment. The LLM weights, system prompts, tool repertoires, and in-context harnesses are frozen at deployment time, and any improvement requires a manual loop of human-curated data collection, offline fine-tuning, modification of the agentic paradigm, and re-deployment. Recent work on self-evolving agents, such as OpenClaw for individual users, indicates that the next leap in agent capability will come from agents that continually learn from their own experience. In this paper, we argue that this vision for self-evolving agent deployment is being held back for enterprise-level large-scale agentic service not by reinforcement learning (RL) algorithms but by agentic online RL systems. Specifically, current agentic RL systems and the surrounding observability software stack are inadequate along three essential aspects: (i) there is no standardized agent trajectory data protocol capable of carrying RL learning signals at step granularity across heterogeneous agent paradigms; (ii) there is no enterprise-grade comprehensive data proxy that converts real workloads into governed learning substrates; and (iii) there is no unified agent evolution control plane that automatically decides, based on trajectory statistics, when to update policy weights or evolve the in-context harness. The next generation of agentic RL systems must be co-designed around these three pillars, and we sketch concrete architectures, case studies, and counter-arguments. We instantiate one branch through AReaL2.0, reorganizing existing RL infrastructure into an agent-oriented online RL loop for policy weight updates from deployed workloads.

With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous capability evaluation increasingly important. However, efficiently building an end-to-end, systematic, and comprehensive evaluation pipeline remains a significant challenge. To address this challenge, we introduce A^2E (Agent Auditing Engine), an end-to-end evaluation engine designed for agent harnesses. A^2E leverages our newly proposed Agent Task Protocol (ATP) to enable the rapid integration of evaluation tasks with different harnesses. Through an automatically instrumented Monitor, it captures and generates standardized execution traces during experiments. In the Evaluation stage, A^2E systematically assesses harness capabilities using a suite of multidimensional metrics. Compared with correctness alone, these metrics provide a more fine-grained characterization of differences among harnesses in execution efficiency, tool use, task planning, and error recovery. Experiments conducted with A^2E further reveal that model-harness combinations exhibit substantial performance variation across different types of tasks, and that no single combination consistently outperforms all others across every task. These findings not only demonstrate the necessity of systematic evaluation but also provide useful guidance for the co-evolving of models and harnesses. Our code is available at https://github.com/datamllab/A2E.

Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather than internalized as reusable model capabilities. We introduce SkillGym, a framework that transforms these skills into executable, verifiable training environments for large language model agents. Its skill-to-task pipeline instantiates concrete tasks, verifies outcomes with code-based checkers, and assesses empirical skill dependence through contrastive executions. We construct and release 2,756 environments across 12 categories and collect 8,364 successful trajectories from multiple models and harnesses, averaging 49 tool calls and over 60k logged text tokens. These resources support supervised fine-tuning on verified workflows and reinforcement learning with outcome-based rewards. Under Claude Code, supervised fine-tuning improves Qwen3.5-35B-A3B by 199 Elo on GDPval-AA v2, 19.10 percentage points on Terminal-Bench 2.1, and 28.13 and 12.38 points on SkillsBench v1.1 with and without skills, respectively. Our 35B SkillGym-Agent reaches 51.47\% on skill-assisted SkillsBench, exceeding reported scores for Claude Sonnet 4.6, GPT-5.4 Mini, and DeepSeek V4 Pro. Without skills, it also surpasses skill-assisted bases under Codex and Claude Code, suggesting reusable procedural competence.

Large Language Models (LLMs) have revolutionized various aspects of engineering and science. Their utility is often bottlenecked by the lack of interaction with the external digital environment. To overcome this limitation and achieve integration of LLMs and Artificial Intelligence (AI) into real-world applications, customized AI agents are being constructed. Based on the technological trends and techniques, we extract a high-level approach for constructing these AI agents, focusing on their underlying architecture. This thesis serves as a comprehensive guide that elucidates a multi-faceted approach for empowering LLMs with the capability to leverage Application Programming Interfaces (APIs). We present a 7-step methodology that begins with the selection of suitable LLMs and the task decomposition that is necessary for complex problem-solving. This methodology includes techniques for generating training data for API interactions and heuristics for selecting the appropriate API among a plethora of options. These steps eventually lead to the generation of API calls that are both syntactically and semantically aligned with the LLM's understanding of a given task. Moreover, we review existing frameworks and tools that facilitate these processes and highlight the gaps in current attempts. In this direction, we propose an on-device architecture that aims to exploit the functionality of carry-on devices by using small models from the Hugging Face community. We examine the effectiveness of these approaches on real-world applications of various domains, including the generation of a piano sheet. Through an extensive analysis of the literature and available technologies, this thesis aims to set a compass for researchers and practitioners to harness the full potential of LLMs augmented with external tool capabilities, thus paving the way for more autonomous, robust, and context-aware AI agents.

Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making agent behavior potentially difficult to control. Orchestration frameworks such as LangGraph, DSPy, and CrewAI impose greater structure through explicit workflow definitions, but tightly couple workflow logic with Python, making agents difficult to maintain and modify. In this paper, we introduce AgentSPEX, an Agent SPecification and EXecution Language for specifying LLM-agent workflows with explicit control flow and modular structure, along with a customizable agent harness. AgentSPEX supports typed steps, branching and loops, parallel execution, reusable submodules, and explicit state management, and these workflows execute within an agent harness that provides tool access, a sandboxed virtual environment, and support for checkpointing, verification, and logging. Furthermore, we provide a visual editor with synchronized graph and workflow views for authoring and inspection. We include ready-to-use agents for deep research and scientific research, and we evaluate AgentSPEX on 7 benchmarks. Finally, we show through a user study that AgentSPEX provides a more interpretable and accessible workflow-authoring paradigm than a popular existing agent framework.

Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations, building an AI-driven spreadsheet agent has emerged as a promising research direction. Most existing spreadsheet agents rely on specialized prompting over general-purpose LLMs; while this design has potentials on simple spreadsheet operations, it struggles to manage the complex, multi-step workflows typical of real-world applications. We introduce Spreadsheet-RL, a reinforcement learning (RL) fine-tuning framework designed to train specialized spreadsheet agents within a realistic Microsoft Excel environment. Spreadsheet-RL features an automated pipeline for scalable collection of paired start-goal spreadsheets from online forums, as well as domain-specific evaluation tasks in areas such as finance and supply chain management, which we compile into the new Domain-Spreadsheet benchmark dataset. It also includes a Spreadsheet Gym environment designed for multi-turn RL: Spreadsheet Gym exposes extensive Excel functionality through a Python sandbox, along with a refined harness that incorporates a comprehensive tool set and carefully designed tool-routing rules for spreadsheet tasks. Through comprehensive experiments, we show that Spreadsheet-RL substantially enhances AI agent's performance on both general and domain-specific spreadsheet tasks: it improves Qwen3-4B-Thinking-2507's Pass@1 on SpreadsheetBench from 12.0% to 23.4%, and raises Pass@1 from 8.4% to 17.2% on our curated Domain-Spreadsheet dataset. These results highlight Spreadsheet-RL's strong potential for generalization and real-world adoption in spreadsheet automation, and broadly, its promise for advancing LLM-based interactions with data interfaces in everyday work.

The original Turing Test asks a human judge to distinguish a machine from a person through dialogue. Three quarters of a century later, conversational systems pass this test in casual settings; the interesting epistemological question has shifted. We argue that the relevant modern variant asks not whether a dialogue partner is artificial, but whether it can be trusted. We present RogueAI, an interactive webapp that operationalizes this revisited test as a one-on-two interrogation game: a human player questions two indistinguishable Large Language Model agents, knowing that exactly one of them has been licensed to deceive within a shared fictional scenario. The player's task is to identify the deceptive agent and "shut it off" before a turn budget is exhausted. We further introduce AutoRogueAI, a procedural extension in which players co-design a custom scenario with a narrator agent that secretly chooses its own deception strategy. We describe the framing, sketch the abstract architecture and gameplay loop, and situate the artifact within recent work on LLM deception, social-deduction benchmarks, and scalable oversight via debate. A three-day pilot deployment (467 initiated sessions, 415 completed, 1876 interaction turns in Italian) provides early feasibility evidence and surfaces a concrete tension: the deceptive agent carries a reliable, locally-present linguistic signature - differential helpfulness, brevity, hedging - that a simple heuristic exploits at 75.6% accuracy, yet human players achieved only 56.6%, consistent with ignoring the most diagnostic signal entirely. We discuss what this gap implies for the artifact's use as a data-collection vehicle, a teaching tool, and an evaluation harness for honesty-trained models.

Reinforcement learning with verifiable rewards (RLVR) replaces human preference labels with executable reward functions such as math answer checkers, JSON tool-call validators, and code unit-test harnesses. That makes the reward partly a software artifact: if the verifier is wrong, optimization can learn the bug. We study this failure mode with a lightweight verifier-fuzzing framework that generates adversarial completions, compares buggy and stricter reference verifiers, logs paired decisions, and reports false-positive, false-negative, disagreement, exploit, and uncertainty metrics.

The Model Context Protocol (MCP) standardizes how large language model (LLM) agents discover, describe, and call external tools. While MCP unlocks broad interoperability, it also enlarges the attack surface by making tools first-class, composable objects with natural-language metadata, and standardized I/O. We present MSB (MCP Security Benchmark), the first end-to-end evaluation suite that systematically measures how well LLM agents resist MCP-specific attacks throughout the full tool-use pipeline: task planning, tool invocation, and response handling. MSB contributes: (1) a taxonomy of 12 attacks including name-collision, preference manipulation, prompt injections embedded in tool descriptions, out-of-scope parameter requests, user-impersonating responses, false-error escalation, tool-transfer, retrieval injection, and mixed attacks; (2) an evaluation harness that executes attacks by running real tools (both benign and malicious) via MCP rather than simulation; and (3) a robustness metric that quantifies the trade-off between security and performance: Net Resilient Performance (NRP). We evaluate nine popular LLM agents across 10 domains and 405 tools, producing 2,000 attack instances. Results reveal the effectiveness of attacks against each stage of MCP. Models with stronger performance are more vulnerable to attacks due to their outstanding tool calling and instruction following capabilities. MSB provides a practical baseline for researchers and practitioners to study, compare, and harden MCP agents. Code: https://github.com/dongsenzhang/MSB

Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per (agent, game) pair, focus on single-agent Solo play, and lack unified protocols for evaluating heterogeneous agent classes (commercial VLMs, open-weight VLMs, and specialized game policies) on the same footing. We address these gaps with OmniGameArena, a real-time benchmark of twelve newly built Unreal Engine 5 games spanning Solo (7), PvP (3), and Coop (2) with unified action interfaces, and the Improvement Dynamics Curve (IDC), an agentic-reflection harness in which a tool-using reflector LLM autonomously refines a bounded skill prompt across multiple rounds. Beyond cold-start leaderboard scores, IDC exposes two additional observables for each (agent, game) pair: how the score evolves across reflection rounds, and how the learned skill behaves on held-out task variants. We report these observables for twelve VLM agents on the cold-start leaderboard and four top agents under IDC.

Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their critical role in machine learning infrastructure, their operational challenges and engineering concerns have received limited attention so far. We present an empirical study of 57 evaluation harnesses, deriving a five-stage harness model and classifying 16,560 issues by workflow stage and root cause. Most harness operational challenges concentrate in the Specification stage (41.4% of issues), where harnesses integrate external models, datasets, and scoring judges. The three most frequent root causes of operational challenges are unimplemented features (24.3%), documentation gaps (20.3%), and missing input validation (17.2%), which together account for 61.7% of classified issues, spanning both defects in existing functionality and capability gaps that block intended workflows. Root causes also vary by workflow stage: environment incompatibility and external dependency breakage account for 36.2% of provisioning issues, whereas algorithmic error (25.9%) and validation gap (22.5%) dominate assessment issues. Together, these contributions establish an empirical foundation for treating evaluation engineering as a distinct software engineering concern.

An LLM agent's real-task performance is shaped as much by the harness around its model as by the frozen model itself: its prompts, injected knowledge, runtime control, and configuration. In deployment the harness is often the only lever available, so improving it automatically is the natural way to raise performance without touching the weights. The hard part is not generating changes but knowing which one truly helped. Self-generated feedback is noisy, and an apparent gain can be a measurement artifact or an edit that merely overfits the tasks it was tuned on. We present a self-evolving agent-harness framework that separates proposing changes from crediting them: a language model diagnoses failures and proposes patches, while all sampling, measurement, and significance testing are owned by deterministic code, so every credited improvement is trustworthy by construction. Patches populate a gated, categorical quality-diversity archive (GSME) keyed on the (WHERE x WHY) pathology an edit addresses rather than the tasks it fixes, an anti-overfitting inductive bias; generalization is measured on a sealed test scored only after evolution. Across seven domains with a frozen open-weight model, the harness is train-selected and scored once on a sealed test; its credited gains there are +9 to +15.5pp and retain 86-147% of the training gain, evidence they generalize rather than overfit. The winning patch tracks the model's dominant pathology, not its size or family: changing the model can change the pathology and the patch, while the same pathology-to-patch match recurs across two model families. What transfers is the diagnose-and-credit loop, not any specific harness.

Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research trajectories are generated, evaluated, and learned from. Existing pipelines typically train models under a fixed harness, including prompts, tools, skills, middleware, and memory, while leaving the data-generating process outside the optimization objective. This creates a mismatch between model updates and the static scaffolding that determines trajectory quality. We introduce Co-Harness, a framework that jointly optimizes the agent harness and model parameters during post-training. Co-Harness alternates between harness optimization and model optimization. An LLM-based HarnessCritic analyzes failed trajectories, identifies harness-level failure modes, and proposes validated local updates. The model is then fine-tuned on high-quality trajectories generated by the improved harness, distilling effective scaffolding into model parameters. A 200+ hour autonomous case study further shows that Co-Harness can recover from system crashes, improve inference efficiency, and discover ensemble strategies without human intervention. These results suggest that joint harness and model optimization is an effective way to improve agents beyond fixed-harness post-training.

As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them. This makes automated harness optimization -- the iterative and evaluation-guided improvement of a harness by an AI system -- both an important route to improving AI systems and a demanding capability for AI systems themselves. Yet the community lacks a common protocol for measuring how well frontier LLMs perform at this task. We introduce HarnessOpt-Bench, a benchmark for end-to-end harness optimization under expensive and stochastic evaluation. An optimizer, an LLM paired with a coding harness, receives a target agent's seed harness, graded evaluation feedback, and a fixed target-evaluation budget. It edits the harness and nominates a final candidate, which is scored by its normalized gain over the seed on a held-out test partition that remains inaccessible throughout search. A trusted execution environment enforces the evaluation boundary, meters target-agent resource use, and preserves candidate versions for audit. We evaluate 5 frontier LLMs as optimizers both under a shared coding harness and under their native harnesses across 4 downstream tasks, over 111 scored runs. Experiment results show that optimizer models separate more than the coding harnesses they act through, native harnesses are not consistently superior, and gains vary substantially across tasks and seed regimes. These results establish harness optimization as a measurable and discriminative capability with large space for improvement.

The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering.

Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the harness---is typically treated as a fixed artifact after deployment. This work studies an alternative where the harness is task-specific and continuously evolvable: each task family maintains its own harness, which is hot-swapped across iterations through a fixed task-injection seam and rewritten using environment feedback. We introduce Hierarchical Self-Improvement (HSI), a framework in which a single frozen LLM M operates across three hierarchical scopes: a task harness H that executes tasks, an evolver that rewrites H, and a meta-evolver that rewrites the evolver's strategy code under a frozen outer anchor. A thinking-on/off design isolates the contribution of harness evolution by disabling reasoning during task execution while enabling it during self-modification. HSI is bounded by two factors: a feedback-fidelity bound, since evolution requires informative reward signals to guide selection, and a backbone capability bound, since harness redesign cannot overcome limitations of the frozen model. On BALROG with DeepSeek-V4-Flash-Preview as the frozen backbone, HSI achieves consistent gains over the initial harness on moderate-difficulty tasks (+39.3 on BabyAI, +33.0 on Crafter, +25.0 on TextWorld, and +15.0 on MiniHack, all in raw \% Progress), while obtaining strong held-out generalization on BabaIsAI sub-suites (0.98 best-test on BreakStop and 1.00 on GoTo from a 20% unseen split). On tasks beyond the backbone's capability (NLE), harness evolution provides no improvement. These results demonstrate task-specific harness evolution as a viable axis for improving frozen LLM agents under clear empirical limits. Code is available at https://github.com/TailinZhou/hsi.

An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling. While harness design strongly affects agent behavior, most automatic improvement methods optimize narrower artifacts such as prompts, pipelines, or workflows, and deployed agents usually reuse a single global harness for all cases. We introduce MemoHarness, an adaptive harness optimization framework that learns from its own executions. MemoHarness decomposes the harness into six editable control dimensions, stores per-case diagnoses and distilled global patterns in a dual-layer experience bank, and adapts the learned harness to each test case using retrieved experience without test-time labels, feedback, or additional search. In our evaluation across shell-agent, code-generation, and analytical-reasoning benchmarks, MemoHarness improves over the fixed harnesses we compare against and shows selective transfer to unseen suites and base models. Its additional context can also remain cost-competitive when much of the retrieved experience is cacheable. These results provide evidence that execution experience is a practical substrate for building agent harnesses that are more adaptive than a single static configuration, while leaving broader claims about statistical robustness and component attribution to future work.

Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Because the value of each design choice is observable only through execution, tailoring a harness to each query has required either executing alternatives at inference time or costly manual design. We introduce SHIFT, which moves execution out of the per-query search loop. A local LLM architect learns a policy over harness-building actions from search, and a value function that predicts, from measured executions, a utility balancing accuracy against execution cost. For each query, Monte Carlo tree search uses these predictions to construct a harness. Across 9,193 tasks in six benchmarks, from math to document and general-assistant tasks, with a Gemini 3.5 Flash executor, SHIFT attains the highest mean accuracy, about 80%, outperforming 17 baselines that span prompting, prompt optimization, and workflow search, and exceeding the strongest baseline by 7.2 percentage points. A cheaper mode of SHIFT also attains a higher mean accuracy than every baseline while using 32% fewer execution tokens than the strongest baseline. We further show that choosing structure, instructions, and tools jointly beats choosing only instructions or only tools by up to 9.1 percentage points, and that learned value selection identifies more accurate harnesses with lower execution cost from candidate pools.