Daily Papers

It is common to train Large Language Models (LLMs) for agentic tasks with Reinforcement Learning (RL) from scalar rewards. However, this throws away the fine-grained information about the environment that the agent experienced during the trial (e.g., error logs). To utilize this rich information, recent works wrap the agent in a harness that refines its own inputs through reflection or compaction and hands past experience to future rollouts, but the construction of the handed-off artifacts (e.g., a playbook) is itself not learned. We want the best of both worlds: gradient updates from a scalar reward, while also utilizing environment information to hand off experience. As a concrete testbed, we fix the Agentic Context Engineering () harness and train one model to act, reflect, and curate task-local playbooks. Our method, , evaluates candidate experience-handoff artifacts by their downstream effect on future actor rollouts, and co-optimizes the role-specific behaviors (action generator, insight reflector, and playbook curator) under a fixed scaffold. Across agentic benchmarks, achieves higher held-out performance than baseline methods. The results suggest that agent training should optimize not only the actions in the current rollout, but also the model-written experience that future rollouts inherit.

Large language model (LLM) agents coordinate complex tasks through multi-role and multi-stage workflows. Upstream state is repeatedly transformed into intermediate language artifacts, such as summaries, plans, tickets, memories, and handoff notes, from which downstream components act. For action-constraining state, topical retention is insufficient: an artifact may mention an unresolved condition while changing it from a requirement that must be resolved before execution into information that may merely inform the next action. We study this action-binding role as operational state preservation. Safety blockers provide a controlled instance because each source state has an explicit prerequisite, authority, fallback, and execution consequence. We condition on correct upstream identification, vary the handoff transformation, and evaluate an executor restricted to the resulting artifact. Across 1,296 controlled synthetic episodes, direct-handoff controls preserve every blocker, whereas compression, plan assimilation, convergence, ownership deferral, and precedent substitution repeatedly turn binding state into caveats or non-binding considerations. Normal handoff compression produces 100.0% deactivation and 54.2% forbidden action. Restoring all four state fields raises preservation to 100.0% and reduces forbidden action to 0.0%. Fixed-artifact interventions further separate preservation from containment: downstream verification eliminates forbidden action while artifact deactivation remains 95.3%. These results identify a state-transmission failure between information extraction and action. Handoff transformations can retain state content while weakening its constraints on downstream action. Semantic availability does not guarantee operational preservation.

Frontier models can now perform well on individual embodied navigation tasks through multi-round multimodal reasoning with simple tools. Across successive tasks, however, an agent must also rely on an evolving map and earlier search records, both of which may be incomplete or conflict with new observations. We present NavHarness, a training-free embodied harness towards lifelong navigation that makes memory processing part of the navigation loop. During navigation, its multi-round agentic session draws on maps, task records, and house knowledge, checking them against observations and recording corrections to guide its actions. NavHarness preserves this experience across fresh conversations for new tasks or recovery attempts, while outcome verification and run-end summaries support its later reuse. On GOAT-Bench, NavHarness improves s-SR over context-only independent sessions by 18.6 points with Astra and 22.6 with Opus 5. Using SLAM-estimated poses, NavHarness with GPT-6 Astra achieves state-of-the-art task success of 83.7 s-SR with 36.9 e-SR on GOAT-Bench and 85.9 s-SR on IR2R-CE. To understand these gains, we examine how experience is carried between sessions and find that structured recovery handovers outperform length-matched summaries. In extended deployments across houses, consolidation improves navigation beyond retaining maps and task records, with case studies showing how agents use earlier experience to interpret new goals, investigate unresolved questions, and resume failed searches. We suggest that progress towards lifelong navigation depends on how successive reasoning sessions build on prior experience, alongside improvements in single-task capability.

Recent work leverages the expressive power of generative adversarial networks (GANs) to generate labeled synthetic datasets. These dataset generation methods often require new annotations of synthetic images, which forces practitioners to seek out annotators, curate a set of synthetic images, and ensure the quality of generated labels. We introduce the HandsOff framework, a technique capable of producing an unlimited number of synthetic images and corresponding labels after being trained on less than 50 pre-existing labeled images. Our framework avoids the practical drawbacks of prior work by unifying the field of GAN inversion with dataset generation. We generate datasets with rich pixel-wise labels in multiple challenging domains such as faces, cars, full-body human poses, and urban driving scenes. Our method achieves state-of-the-art performance in semantic segmentation, keypoint detection, and depth estimation compared to prior dataset generation approaches and transfer learning baselines. We additionally showcase its ability to address broad challenges in model development which stem from fixed, hand-annotated datasets, such as the long-tail problem in semantic segmentation. Project page: austinxu87.github.io/handsoff.

Language-model agents can accumulate interaction feedback, but reliably turning that feedback into reusable experience remains challenging. Existing methods either optimize external experience scaffolds or train experience-related behavior on specific task distributions, leaving open whether experience learning itself can become a transferable model capability. Training such a capability calls for supervision beyond isolated tasks, which mainly support in-episode problem solving rather than revealing what knowledge remains useful across episodes. In this work, we introduce MetaExp, a scalable framework that trains this capability through verifiable task families with controlled cross-task structure. Each family preserves a reusable factor while varying task-specific realizations, enabling transfer without direct solution reuse. We propose two complementary designs: Shared-Tool families keep black-box tools fixed across tasks to elicit operational experience, while Shared-Workflow families preserve latent procedures across changing realizations to elicit procedural experience. We scale environments under both designs, collect and filter sequential interaction trajectories, and fine-tune Qwen3.5-122B-A10B on 4,956 trajectories from 1,000 task families. With parameters frozen during downstream evolution, MetaExp improves by +8.5 points on SpreadsheetBench, peaks at +2.3 on APEX-Agents, and improves by +14.8 on AutomationBench. The gains persist under domain-excluded training, supporting experience learning as a transferable capability for continued non-parametric improvement after deployment.

Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a cache of prior conversations. It should serve as a continuity and governance substrate: preserving durable user state, grounding answers in multimodal and device evidence, supporting correction and forgetting, bounding policy evolution, and remaining deployable under latency, cost, privacy, and edge-cloud constraints. This technical report presents Mi-Memory, a lifecycle memory framework for Personal AI organized around four roles: Structure, Expansion, Evolution, and Deployment. A shared audit contract links these roles through four recurring artifact families: typed evidence payloads preserve source identity and provenance, diagnostic traces localize evidence loss across the serving pipeline, strategy artifacts make memory-policy changes explicit, and gate/rollback records bound accepted evolution. MiMemory instantiates the roles through MemStack, MemSense/MemFuse, D^{2}ACCI/E^{2}MEND, and LiteMem. In controlled-reference Structure evaluations, MemStack reaches 93.59%, 57.24%, and 87.47% on LoCoMo, PersonaMem-V2, and LongMemEval, respectively; other tracks report module-level, preliminary/internal, transfer-feasibility, or design-only evidence with explicit boundaries. MiMemory is a step toward auditable, evidence-gated, and deployment-aware memory systems for Personal AI. Project homepage: https://darwin-agent.github.io/Mi-Memory/ .

Full-duplex voice agents can now listen, speak, use tools, and act during spoken interactions, but fluent dialogue does not guarantee correct completion of delegated professional workflows. We introduce APEX-Voice, a benchmark of 120 interactive professional workflows spanning ten work archetypes such as form completion, corporate negotiation, coordination, consulting, and interviewing. Each workflow executes in a stateful Voice Workbench environment with task-specific knowledge, typed tools, gold-annotated final work artifact, authorization constraints, and a user simulation policy backed by validated, pre-compiled speech realizations. We evaluate both artifact field accuracy and end-to-end workflow success, which requires the correct terminal state, valid process, completed actions, and a valid final artifact. Across five frontier real-time voice agents-GPT-Live-1, Gemini-3.8-Live, Grok-Voice-Think-2.0, Step-Audio3, and GPT-realtime-2.1, none exceeds 25% Pass@1, and the best Reliable@3 is only 10.8%. Moreover, stateful coordination is the dominant failure point across systems, while success decreases further on workflows requiring greater knowledge retrieval and mid-speech corrections. Overall, APEX-Voice is the first benchmark for evaluating whether voice agents can translate conversational competence into dependable professional work.

Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child inherit the parent's full working context. We measure how the effect of inherited state changes with capability, where C_m denotes clean fork-fresh accuracy. We compare 3 inheritance policies: Reset (fork fresh: base evidence only), Selective (curated handoff: + the useful prior conclusion), and Full (implicit fork: + the useful conclusion and d copies of a superseded conclusion) over a same-family ladder (Qwen3 0.6/1.7/4/8B) on a frozen, closed-set, action-scored benchmark. Every task is solvable from the base evidence, so performance loss can be attributed to reliance on stale state. (1) Deference to superseded state falls sharply with measured capability C_m (the slope's confidence interval, CI, excludes zero on every family) across 2 synthetic primitives plus MuSiQue and HotpotQA. (2) On the Qwen3 synthetic ladder, net inheritance harm follows a nonmonotone pattern: a mid-capability model (Qwen3-1.7B) is a statistically significant local minimum of net harm, falling below its fork-fresh baseline (Δ(32)=-0.19 [-0.25, -0.12]) and both neighbors, while the weakest model stays near-neutral and the strongest models stay robust. We call this harmful capability range a danger band. A within-model counting-difficulty sweep shows that the effect depends on model class even at matched C_m, and a live parent-to-child fork reproduces the mid-model harm. (3) Curated Selective handoff improves average accuracy over Full on all 3 datasets, largest at the in-band model, while the fixed-threshold capability router fails on the other datasets; a transferable router would need to predict the balance between reuse benefit and stale-context penalty. The benchmark is frozen and version-hashed.

Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue. Real software work is messier: tasks are interrupted, reassigned, reviewed, and resumed from partial states left by another agent or engineer. We study this missing dimension through handoff debt: the rediscovery cost imposed when a predecessor's work is opaque or incomplete. Our takeover protocol interrupts a coding agent at deterministic handoff points, freezes the repository, and evaluates successor agents under four handoff views: repository state only, raw trace, summary notes, and structured notes. Across 75 source tasks, the protocol generates 181 handoff-point tasks and 724 takeover runs per successor model. Across three successor models, context-bearing handoffs reduce median agent events by 20-59% and cumulative prompt tokens by 42-63% relative to repository-only takeover. Solved-rate effects are smaller and model-dependent, but efficiency gains are consistent. These findings suggest that coding-agent evaluation should report not only whether a task is solved, but also how costly that work is for another agent to resume.

Tool timeouts can leave AI agents facing ambiguous tool outcomes and partial execution: an action may have failed, committed or remained in flight while other workflow steps have already completed. We formulate evidence-guided task recovery over approved obligations, provider capabilities and states compatible with public evidence. A shared admissibility check handles key expiry, authorization timing, dependencies and residual effects; a terminal certificate separates actual goal satisfaction from publicly supported safe completion. The known-model implementation combines standard observation-contingent planning with a separately implemented effect-history adjudicator. In a finite study of 37 assignments, planning and three active controls each certify 28 completions; four saved synthetic fee units incur additional computation. A preregistered assignment-held-out comparison then evaluates planning advice against evidence prompting with two local model bundles. Across 58 paired units in 19 previously developed task families, advice certifies 30 completions versus 9, a 36.2-percentage-point difference (exact family sign-flip p=0.0078), using 272 proposals versus 399. All 116 trajectories pass independent replay. Both models exhibit a positive completion difference. The comparison measures the evaluated advice interface under a common shield; search-versus-rule advice requires a separate matched comparison. Unknown and handoff outcomes remain explicit, with guarantees tied to the declared provider capabilities rather than arbitrary third-party exactly-once execution.

Foundation models are moving from response generation into operational roles. They plan across steps, call tools, request human input, coordinate with other agents, and increasingly carry responsibility for work that affects customers, claims, code, contracts, and clinical decisions. Production deployments are no longer one human supervising one model. They are multi-human, multi-agent collaborations that cross teams, time zones, and trust boundaries. The technical surface for this collaboration remains weakly specified. When an agent drafts a response and a human edits it before it ships, the moment of human judgement is the most valuable signal in the system. In current practice it is recorded, if at all, in application code, chat threads, ticket comments, and tribal memory. Two protocol standards address adjacent concerns: MCP standardises agent access to tools and data, and A2A standardises agent-to-agent interoperability. Neither defines the shared workspace in which humans and agents perform accountable work together. This paper presents CHAP, the Collaborative Human-Agent Protocol. Under CHAP, the override that used to vanish into a chat thread becomes a structured event carrying a diff, a rationale, and a content hash. The handoff between shifts becomes a portable envelope rather than a pinned message. The human approval of an agent's draft becomes a non-repudiable signed decision that can be replayed years later. The protocol achieves this through a small Core (workspaces, participants, tasks, artefacts, and an append-only evidence log) together with composable profiles that add review, modes, routing, deliberation, handoff, identity, signatures, and transparency-backed audit as deployments require them. Specification, reference implementation, conformance suite, and worked examples are available at: https://github.com/BrightbeamAI/chap

Existing evaluations of foundation models, including recent human-centric approaches, fail to capture what truly matters: user's experience during interaction. Current methods treat evaluation as a matter of output correctness alone, overlooking that user satisfaction emerges from the interplay between response quality and interaction, which limits their ability to account for the mechanisms underlying user experience. To address this gap, we introduce QoNext, the first framework that adapts Quality of Experience (QoE) principles from networking and multimedia to the assessment of foundation models. QoNext identifies experiential factors that shape user experience and incorporates them into controlled experiments, where human ratings are collected under varied configurations. From these studies we construct a QoE-oriented database and train predictive models that estimate perceived user experience from measurable system parameters. Our results demonstrate that QoNext not only enables proactive and fine-grained evaluation but also provides actionable guidance for productized services of optimizing foundation models in practice.

Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recurring routines. Existing approaches retrieve task-relevant history and append it to the policy's context, implicitly assuming that experience relevant to a task remains useful for each decision within it. We find that this help is largely spent at the first decision: retrieved history strongly improves the opening step of an episode, yet provides little sustained benefit over the remaining 90\% of steps, and offers weak guidance on whether a proactive suggestion is warranted. A relevant record may tell the agent where to begin, but not which past action applies to the current screen or whether a routine is due now. The underlying issue is that relevance does not imply applicability}: relevance is determined at the task level, whereas applicability depends on the situation at decision time. We therefore recast personalization as experience activation and introduce ExpActivator, a training-free framework that activates only the experience applicable to the current situation. During execution, ExpActivator matches each new screen to historical states in the frozen GUI backbone's latent space and supplies the corresponding action as a reference. Before execution, it activates a recurring intent only when the current time and scenario provide sufficient support, and otherwise abstains. Across four GUI backbones, ExpActivator improves within-trajectory step success by 28\% on average, achieves the best personalized execution on every backbone while using about one-fifth as many history tokens, and reaches approximately 2.3times the Matthews correlation coefficient of the strongest proactive baseline. Experience pays where it is activated, not where it is appended.

Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposals. As evidence accumulates, a central problem emerges: which past update evidence remains actionable after subsequent training has changed the parent model? An update's effect depends on its parent, data, and training stage. Treating past success as context-free permission can waste compute. If the resulting child is promoted, it can also degrade the subsequent training trajectory. We formulate this problem as conditional experience transfer and introduce Boundary-Calibrated Intervention Transfer (BCIT), a method that authorizes experience reuse before weight-changing training. BCIT binds an observed effect to its source context, checks applicability conditions, vetoes candidates with named hard conflicts, and obtains current-state evidence through a bounded training trial when needed. Fully trained candidates still face a shared adoption rule, and only observed events extend memory. On one 4B model adapted across finance reasoning, text-to-SQL, and function calling, candidate updates exhibit heterogeneous target and retention effects across the evaluated contexts. Under matched candidates, evidence, and compute, BCIT authorizes fewer harmful updates and attains higher equal-budget final-model quality than the evaluated alternatives. These results support treating experience authorization as a distinct problem in autonomous post-training.

This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We study this question in 4.590 controlled trials across 45 scientific code-solving scenarios. We find that documentation-oriented Skill packages provide unstable control: their useful signal is sparse, and expanding a compact experience object into a fuller documentation package often fails to help and can degrade the overall average. We further show that representation itself is a first-order factor. A compact Gene representation yields the strongest overall average, remains competitive under substantial structural perturbations, and outperforms matched-budget Skill fragments, while reattaching documentation-oriented material usually weakens rather than improves it. Beyond one-shot control, we show that Gene is also a better carrier for iterative experience accumulation: attached failure history is more effective in Gene than in Skill or freeform text, editable structure matters beyond content alone, and failure information is most useful when distilled into compact warnings rather than naively appended. On CritPt, gene-evolved systems improve over their paired base models from 9.1% to 18.57% and from 17.7% to 27.14%. These results suggest that the core problem in experience reuse is not how to supply more experience, but how to encode experience as a compact, control-oriented, evolution-ready object.

Professionally generated content (PGC) streamed online can contain visual artefacts that degrade the quality of user experience. These artefacts arise from different stages of the streaming pipeline, including acquisition, post-production, compression, and transmission. To better guide streaming experience enhancement, it is important to detect specific artefacts at the user end in the absence of a pristine reference. In this work, we address the lack of a comprehensive benchmark for artefact detection within streamed PGC, via the creation and validation of a large database, BVI-Artefact. Considering the ten most relevant artefact types encountered in video streaming, we collected and generated 480 video sequences, each containing various artefacts with associated binary artefact labels. Based on this new database, existing artefact detection methods are benchmarked, with results showing the challenging nature of this tasks and indicating the requirement of more reliable artefact detection methods. To facilitate further research in this area, we have made BVI-Artifact publicly available at https://chenfeng-bristol.github.io/BVI-Artefact/

Agent Skills have become persistent behavioral artifacts across independent AI agent systems. They combine natural-language task specifications with metadata and optional references, scripts, assets, hooks, package manifests, tests, and companion interfaces. Existing studies explain how Skills are specified, executed, maintained, and evolved, but lack an ontology that defines these artifacts as independent software objects. This paper introduces Skillware as the software abstraction that extends software engineering to persistent Behavioral Artifacts in agent systems. A Skill Artifact specifies reusable task behavior; a Skillware Unit manages that artifact as software through an independent identity and lifecycle. A compatible Agent Host activates the unit for runtime interpretation. Three necessary conditions operationalize category membership: behavioral primacy, independent software identity, and an Agent Host execution relationship. Lifecycle Continuity records whether the same unit identity persists through update, maintenance, rollback, and removal as a separate software-grade property. Evidence combines the Agent Skills specification, a frozen corpus of 138,133 content-deduplicated SKILL.md records associated with 20,556 repository identifiers, independent empirical studies, 15 category-boundary cases, and 13 fixed-revision engineering implementations. The evidence establishes a recurring artifact envelope, separable software identities, compatible execution paths, and lifecycle engineering pressure. Skillware provides the software ontology and engineering lifecycle through which agent capabilities can become identifiable, composable, maintainable, and evolvable software artifacts.

Long-running Large Language Model (LLM)-based agents often accumulate large intermediate traces containing audits, eliminations, and numeric calculations. In practice, this state is compressed before handing it to a downstream decision step, creating an information bottleneck in which small omissions can break strict numeric or categorical constraints. This paper evaluates hand-off compression in a closed-world travel-planning relay with two LLM agents. A Researcher audits a fixed inventory of hotels and flights for 50 goal instances, and a Booker selects a hotel--flight pair using only the goal and the hand-off payload, with the inventory withheld. We compare four hand-off conditions: no compression, narrative summarization, schema-constrained JSON extraction, and embedding-based pruning. Exhaustive enumeration over the fixed inventory provides exact feasible and optimal labels. Results show that hand-off representation strongly affects downstream feasibility under a small decision model. JSON extraction achieves the highest feasibility accuracy at 0.96, while narrative summarization, despite producing the smallest compressed hand-off payload, degrades feasibility to 0.48. Embedding-based pruning matches the uncompressed control on feasibility at 0.88 without an additional generative compression call. These findings indicate that constraint checking benefits from structured and auditable hand-off representations rather than relying on brevity alone.

Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluations do not show whether those systems improve executable repository work. Repository benchmarks test code changes but do not isolate memory, while memory benchmarks score recall without measuring downstream coding outcomes. We introduce VibeMemBench, a benchmark for evaluating memory systems on 111 coding targets from 90 SWE-rebench V2 repositories and 3,634 history trajectories from the target repositories. The targets follow the SWE benchmark style and cover bug fixes, feature requests, interface changes, and configuration work. An agent edits each target codebase under a declared memory condition. Executable tests decide task resolution. Each target is retained only when injected history experience improves its executable outcome in a reference setting, so every target carries a prior experience whose usefulness is verified by execution in that setting. The frozen verified experience is then transferred to five held-out solvers. Direct injection raises observed task resolution on four of them by 1.1 to 4.5 percentage points while lowering agent steps on all five. Yet when four existing memory systems must construct and retrieve experience from the same history, eleven of twelve solver and system pairings fail to exceed the matched memory-off baseline. VibeMemBench exposes the gap between the useful experience that repository history holds and the experience existing memory systems deliver for repository coding tasks.

Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve. We introduce EvoGenUI-Bench, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scenarios: information presentation, executable interaction, and tool-grounded external state. We execute generated artifacts in a browser and evaluate them using screenshots, source and DOM evidence, actor traces, and runtime logs. Beyond turn-level and episode-level success, we measure cross-turn retention with Adjacent Pass Retention. Across eight models, even the strongest achieves 74.9% Turn Pass while completing only 37.3% of five-turn episodes; APR further falls to 52.4% on tool-grounded tasks. Diagnostic analysis shows that presentation failures center on information architecture, interaction failures on derived-state propagation and affordance binding, and tool-grounded failures additionally involve external-state grounding and requirement decomposition. These results reframe generative UI evaluation from judging isolated outputs to testing whether interface behavior, derived state, external state, and assistant claims remain synchronized as the artifact evolves.

Grounded language-model pipelines can be divided into three stages: selecting an object, retrieving passages for it, and using that evidence to answer. If the selected object must reach the reader, losing it breaks the handoff. Benchmark recall checks the dataset-linked object, which can differ. We audit 600 HybridQA questions across three selector families. On 1,463 resolvable records where the selected object matches the dataset-traced passage, exact key lookup and exact title matching return the object every time. With every ranked rule given the same decoded selected title, body-only BM25 omits it on 389 records (26.6%) at cutoff five, while hybrid retrieval with reranking omits it on 14 (1.0%). The two identities differ on 329 of 1,792 resolvable records. With original-question rankings, their top-five checks disagree on 106 records (5.9%). Frozen reader comparisons associate the aligned object's presence with 28.6 to 31.0 points higher exact match. In a deliberately selected 64-item cohort, removing that passage sharply lowers exact match, while removing a similar-length comparison passage does not reproduce the drop. We release the Returned-Object Profile (ROP), an executable record of the target, returned-ID field, cutoff, membership rule, and complete expected population, with data and an offline replay.

Runtime-governance evidence often collapses materially different events into one audit record: a decision may be made, an instruction dispatched or received, an action may or may not execute, and a resulting state may or may not be observed. This paper presents AIREP, a vendor- and model-independent protocol for per-decision AI runtime evidence. Its current wire model separates evidence into four artifact families: Decision, Control, Execution, and Effect. Artifacts use closed core schemas, explicit identities and digests, declared scope limits, RFC 8785 canonical JSON, domain-separated SHA-256 hashing, and pure Ed25519 signatures. A three-level assurance model distinguishes structural/hash consistency (AIREP-Core), verifier-accepted authorship (AIREP-Authenticated), and independently anchored chain-head freshness and non-truncation relative to an accepted witness (AIREP-Witnessed); these classes do not establish event truth. A structured reconciler preserves failure, missing evidence, unevaluated prerequisites, and indeterminate outcomes as distinct states. The released beta includes a four-family first-party producer, Python and Node reference-verification paths, adversarial/lifecycle corpora, and reproducible validation. Post-release first-party Hermes and LightEval integration exercises preserve explicit evidence boundaries without claiming adoption or interoperability. Independent implementation evidence exists separately for a v0.1.2 producer and a v0.2 consumer/verifier; because they target different frozen versions, they do not establish same-version producer-to-consumer interoperability. AIREP remains experimental.

Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are generally more reliable but more costly. This reliability-cost trade-off motivates routing methods that decide when to invoke an agent with a larger backbone: before execution, after a fixed trajectory prefix, or locally at individual steps. Our method, TACIT-SWITCH, learns permanent handoff policies from accumulated trajectory evidence and Teacher-Annotated Censored Intervention Times (TACIT). It represents each annotation as an interval-censored observation on a cumulative-risk scale. The resulting mixture-cure threshold model estimates the probability that the paired Strong rollout succeeds and, conditional on success, the handoff threshold; no teacher is required at deployment. In a mechanism-based multi-step simulation, TACIT-SWITCH improves success by 7.4-11.1 percentage points over task-level, step-level, and fixed-prefix routing baselines at comparable cost. Within that controlled simulation, ablations show that task features and cumulative trajectory risk provide complementary information. With operating points selected on development data, TACIT-SWITCH achieves the highest held-out success among learned policies on both ALFWorld (48.5% with 4B Cheap; 45.5% with 9B Cheap) and DABench (73.1%).

Benchmarks are necessary for healthcare evaluation, but are not sufficient for predicting deployment performance. Our position is that the evaluation--deployment gap arises not because of poorly designed benchmarks, but from implicit assumptions about how users interact with models that cannot be surfaced from benchmarks alone. To make this precise, we propose a classification of assumptions into two categories: task, which can be tested from conversation data alone, and outcome, which requires outcome data and behavioral studies for testing. Critically, outcome assumptions depend on human behavior, something that even well-designed benchmarks cannot directly observe. To demonstrate the operationality of this framework, we retrospectively analyze a healthcare RCT as a case study and find that the gap naturally separates into task and outcome gaps of roughly equal size. To address this, we make two contributions: first, we propose BenchmarkCards, an artifact that documents assumptions, and second, we propose staged evaluation, a procedure that systematically tests assumptions and evaluates performance.

Solving long-horizon agentic tasks requires language agents to interact with their environments over multiple steps, and reliable performance often comes from the expensive capable models available through cloud providers. Meanwhile, alternative efficient models with inferior performance but a much lower cost are emerging, including lower-tier cloud models and smaller open-weights models deployable on local hardware. This raises a natural question that remains less explored than traditional query-level routing: can capable and efficient models collaborate within a single long-horizon agentic task to substantially reduce cost while preserving task accuracy? In this paper, we systematically investigate key design choices for such collaboration through model handoffs, where one model takes over from another, focusing on handoff direction and context transfer. We find that efficient-to-capable handoffs generally underperform capable-only execution with limited or even no cost reduction, whereas capable-to-efficient handoffs at suitable stages of task progress largely preserve or even improve accuracy while substantially reducing cost. These findings suggest that a one-time, simple, well-timed handoff strategy is good enough for cost-effective agent collaboration, motivating AgentBaton, a lightweight detector that learns when to hand off from recurring patterns in task progress. Across 11 model pairs and two representative benchmarks, AgentBaton reduces API costs by 65.9% on average while largely preserving task accuracy, with accuracy gains of up to 8.8 percentage points over capable-only execution. Experiments across various reasoning-effort settings further show that AgentBaton extends the empirical accuracy-cost Pareto frontier.

Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs). While prior work has predominantly focused on single-iteration transfer, we discover that under multi-iteration experience learning, existing methods suffer from a progressive capability collapse rather than compounding improvement. We systematically examine this failure through three vital dimensions of experience internalization: (1) Experience Granularity: We find that principle-level experience is more durable than instance-level experience, as it effectively abstracts transferable strategies away from trajectory-specific details. (2) Experience Injection Pattern: Our analysis reveals that step-wise injection significantly outperforms global injection by aligning experience with intermediate decision states, a property that is critical for long-horizon tool use. (3) Internalization Regime: We demonstrate that off-policy context-distillation on high-quality teacher trajectories provides a substantially more stable training signal than on-policy context-distillation, which is inherently limited by local corrections on student-induced flawed states. Together, these insights yield a simple yet robust recipe for stable and sustainable experience internalization, providing concrete guidance for engineering self-evolving and continually learning LLMs.

Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for studying this capability because they retain preferences, task histories, tool routines, and learned skills across sessions. Yet whether retained experience actually improves them over time has not been systematically tested. We introduce PAST-Bench, a benchmark designed to isolate this question. Each agent runs through ordered sequences of fresh-session tasks under matched conditions that turn retained experience on and off. It spans 26 scenarios and 204 episodes across memory, procedural reuse, information gathering, and update. We report both later-task gains and whether those gains follow the intended save, retrieve, and update pathway. Across seven base models and four agent frameworks, improvement is real but uneven across capabilities. Agents with the same headline gain can differ markedly in whether that gain is supported by evidence of the intended pathway. Guided by these findings, we develop Hermes+, which extends Hermes with five targeted interventions across stages of the agent loop. Hermes+ raises the average gain from retained experience and provides clearer pathway evidence, with its strongest improvement on tasks requiring outdated state to be replaced, although the effect remains capability- and model-dependent. Together, PAST-Bench and Hermes+ provide an evaluation and diagnostic foundation for studying how persistent agents can progress from retaining experience to systematically improving through it. Code: https://github.com/Gen-Verse/PAST-Bench

Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation. To understand the current state of this capability, however, evaluation must go beyond final scores, which neither reveal where progress is gained or lost nor indicate whether accumulated experience improves later decisions. We therefore present a systematic evaluation of seven frontier models on 36 long-horizon tasks based on a new framework that uses rule-based metrics to characterize within-run behavior through Solution Framing, Execution, and Feedback Control and controlled comparisons to assess experience reuse within and across tasks. The results show that current agents operate more like engineering optimizers than fully autonomous researchers: they can formulate and implement practical solutions, but their performance varies substantially across runs, their strongest solutions mainly adapt or combine established techniques, and genuine methodological novelty remains rare. Detailed analysis reveals that observed performance is shaped by multiple factors, including distinct process bottlenecks behind similar final outcomes, experience reuse that can help or mislead subsequent decisions, and harness designs that affect performance stability. These findings suggest concrete directions for improving model training, inference-time strategies, experience management, and harness design.

Modern image generators produce strikingly realistic images, where only artifacts like distorted hands or warped objects reveal their synthetic origin. Detecting these artifacts is essential: without detection, we cannot benchmark generators or train reward models to improve them. Current detectors fine-tune VLMs on tens of thousands of labeled images, but this is expensive to repeat whenever generators evolve or new artifact types emerge. We show that pretrained VLMs already encode the knowledge needed to detect artifacts - with the right scaffolding, this capability can be unlocked using only a few hundred labeled examples per artifact category. Our system, ArtifactLens, achieves state-of-the-art on five human artifact benchmarks (the first evaluation across multiple datasets) while requiring orders of magnitude less labeled data. The scaffolding consists of a multi-component architecture with in-context learning and text instruction optimization, with novel improvements to each. Our methods generalize to other artifact types - object morphology, animal anatomy, and entity interactions - and to the distinct task of AIGC detection.

Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent learning for rapid reuse. This limitation is especially important for Web agents that repeatedly execute related multi-step workflows. We propose HaMo, a Harness-Model collaborative framework that combines fast non-parametric experience accumulation with slow parametric adaptation. HaMo distills trajectories into strategy-level experience cards for immediate retrieval, while an experience-conditioned continual learning objective trains the model to interpret, ground, and execute retrieved strategies across changing contexts. A retrieval-coverage-based selection mechanism further identifies compact and complementary trajectories for parameter updates. Experiments show that HaMo outperforms harness-only and model-only adaptation under within-domain and cross-domain shifts, improving both retention and adaptation. These results highlight the importance of jointly preserving procedural experience and internalizing the competence to transfer and execute it across tasks.

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.

Autonomous agents powered by large language models (LLMs) show significant potential for achieving high autonomy in various scenarios such as software development. Recent research has shown that LLM agents can leverage past experiences to reduce errors and enhance efficiency. However, the static experience paradigm, reliant on a fixed collection of past experiences acquired heuristically, lacks iterative refinement and thus hampers agents' adaptability. In this paper, we introduce the Iterative Experience Refinement framework, enabling LLM agents to refine experiences iteratively during task execution. We propose two fundamental patterns: the successive pattern, refining based on nearest experiences within a task batch, and the cumulative pattern, acquiring experiences across all previous task batches. Augmented with our heuristic experience elimination, the method prioritizes high-quality and frequently-used experiences, effectively managing the experience space and enhancing efficiency. Extensive experiments show that while the successive pattern may yield superior results, the cumulative pattern provides more stable performance. Moreover, experience elimination facilitates achieving better performance using just 11.54% of a high-quality subset.

Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone. We present SuperScout, which routes after scouting the repository: a 7B searcher, SuperScout-7B, first explores the repository and produces a structured handoff whose reproduction claims are sandbox-verified, with false claims stripped before delivery. The searcher's hidden states, together with the task text, then feed a resume-based router that dispatches the task to one of four frontier fixers. Adding a new fixer requires no retraining. On the full Python slice of SWE-bench Pro (266 tasks) under the benchmark's official capped budget tier, SuperScout matches the best single model's solve rate (159 of 266 for SuperScout, 158 for the best model) at about a fifth of the total cost per solve, and the reported configuration sits above the random traffic-splitting baseline. A no-router ablation, always the cheapest fixer with the handoff, ties the routed system on this benchmark, so the handoff rather than the routing decision carries the result. A paired calibration study points to the mechanism: the handoff appears to redistribute rather than add solving ability, lifting the three cheaper fixers while slightly hurting the strongest, though at N=99 the per-fixer effects are directional only; the searcher's hidden states improve cost routing on the calibration labels while the handoff's own text does not. The searcher's compute adds less than half a cent of GPU time per task.

Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact in isolation that each re-extract the paper from scratch, usually ship one-way renders the author cannot reopen in PowerPoint or Word, and gates quality on soft VLM-preference scores that plateau while load-bearing sections still read as empty. We argue this last mile is best built as a composition of skills: thin agent-readable contracts that share one upstream extractor and wrap deterministic primitives in a measured-fill loop whose exits are hard pass/fail render gates. We instantiate this as ResearchStudio-Reel, five Claude Code and Codex skills organized into one shared extractor (Paper2Assets), three editable generators (Paper2Poster, Paper2Video, Paper2Blog), and one interactive convergence layer (Paper2Reel). Paper2Assets extracts each paper once into a shared bundle that can be reused by every downstream skill; The three generators produce a print-ready poster, a synchronized talk video, and a bilingual blog that stay factually consistent and round-trip through PowerPoint or Word; Paper2Reel then binds all three into a self-contained HTML viewer whose section-level clicks jump the video, slides, captions, and blog to matching content. On the Paper2Poster benchmark, our posters lead every aesthetic and information sub-criterion against both prior automated systems and single-shot frontier LLMs, surpassing the authors' own on aesthetics under two held-out VLM judges and winning overall on 84% to 93% of papers; capability audits further show that, by uniquely pairing narration-aligned on-slide highlights with a bilingual blog gated by layout-aware DOCX repair, ResearchStudio-Reel is the only pipeline to ship all three editable artifacts. Project is available at https://aka.ms/ResearchStudio

When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory. Developers must then inspect the full execution to identify the responsible role and localize the earliest decisive root-cause step. Existing failure-attribution benchmarks largely focus on shorter traces, leaving diagnosis across hundreds of recorded steps underexplored. We introduce LongRCA Bench, comprising 1,140 failed trajectories across five domains without injected errors. It provides independently scored human labels for the responsible role and earliest decisive root-cause step. The median trajectory contains 145 steps, and the strongest baseline reaches only 13.2% exact root-step accuracy. We further present Root-Cause Trajectory Attribution (RCTA), a training-free method that retrieves candidate error steps from segment summaries and traces them to available earlier handoff instructions. Using the same backbone, benchmark instances, and scoring protocol, RCTA reaches 51.1% responsible-role accuracy and 24.1% exact root-step accuracy. These results highlight the need to evaluate responsible-role attribution and exact root-step localization as separate targets in long-trajectory failure diagnosis.

The artifact used for evaluating the experimental results of Measuring and Mitigating Gaps in Structural Testing is publicly available on GitHub, Software Heritage and figshare, and is reusable. The artifact consists of necessary data, tools, scripts, and detailed documentation for running the experiments and reproducing the results shown in the paper. We have also provided a VirtualBox VM image allowing users to quickly setup and reproduce the results. Users are expected to be familiar using the VirtualBox software and Linux platform for evaluating or reusing the artifact.

Drone fleets with onboard cameras coupled with computer vision and DNN inferencing models can support diverse applications. One such novel domain is for one or more buddy drones to assist Visually Impaired People (VIPs) lead an active lifestyle. Video inferencing tasks from such drones can help both navigate the drone and provide situation awareness to the VIP, and hence have strict execution deadlines. We propose a deadline-driven heuristic, DEMS-A, to schedule diverse DNN tasks generated continuously to perform inferencing over video segments generated by multiple drones linked to an edge, with the option to execute on the cloud. We use strategies like task dropping, work stealing and migration, and dynamic adaptation to cloud variability, to guarantee a Quality of Service (QoS), i.e. maximize the utility and the number of tasks completed. We also introduce an additional Quality of Experience (QoE) metric useful to the assistive drone domain, which values the frequency of success for task types to ensure the responsiveness and reliability of the VIP application. We extend our DEMS solution to GEMS to solve this. We evaluate these strategies, using (i) an emulated setup of a fleet of over 80 drones supporting over 25 VIPs, with real DNN models executing on pre-recorded drone video streams, using Jetson Nano edges and AWS Lambda cloud functions, and (ii) a real-world setup of a Tello drone and a Jetson Orin Nano edge generating drone commands to follow a VIP in real-time. Our strategies present a task completion rate of up to 88%, up to 2.7x higher QoS utility compared to the baselines, a further 16% higher QoS utility while adapting to network variability, and up to 75% higher QoE utility. Our practical validation exhibits task completion of up to 87% for GEMS and 33% higher total utility of GEMS compared to edge-only.

To enhance the handover performance in fifth generation (5G) cellular systems, conditional handover (CHO) has been evolved as a promising solution. Unlike A3 based handover where handover execution is certain after receiving handover command from the serving access network, in CHO, handover execution is conditional on the RSRP measurements from both current and target access networks, as well as on mobility parameters such as preparation and execution offsets. Analytic evaluation of conditional handover performance is unprecedented in literature. In this work, handover performance of CHO has been carried out in terms of handover latency, handover packet loss and handover failure probability. A Markov model accounting the effect of different mobility parameters (e.g., execution offset, preparation offset, time-to-preparation and time-to-execution), UE velocity and channel fading characteristics; has been proposed to characterize handover failure. Results obtained from the analytic model has been validated against extensive simulation results. Our study reveal that optimal configuration of O_{exec}, O_{prep}, T_{exec} and T_{prep} is actually conditional on underlying UE velocity and fading characteristics. This study will be helpful for the mobile operators to choose appropriate thresholds of the mobility parameters under different channel condition and UE velocities.

In production large language model (LLM) deployments, high API availability guarantees do not equate to conversational continuity. When a primary provider experiences an outage or strict rate-limiting, naive stateless failover mechanisms successfully maintain uptime but silently discard conversation history, severely disrupting the user experience. To rigorously quantify and resolve this failure mode, we introduce two novel metrics: Continuity Preservation Rate (CPR) and Continuity Latency Overhead (CLO). We propose a stateful, multi-provider proxy architecture utilizing a History-Forwarding strategy to seamlessly reconstruct conversational state across heterogeneous LLM endpoints during failover events. Furthermore, we release continuity-bench, https://github.com/Vishal-sys-code/continuity-bench, an open evaluation harness designed to stress-test context preservation under high-concurrency provider failure conditions. Our empirical evaluation (N=750 failover events) demonstrates that our stateful proxy achieves a 99.20\% CPR [95\% CI: 98.27\%, 99.63\%], cleanly transferring deep conversational context to fallback providers, compared to a near-0\% preservation rate for standard stateless architectures. Finally, we characterize failover latency distributions, identifying the critical necessity of asynchronous exponential backoff with jitter to prevent cascading retry storms against strict-limit fallback APIs. Our results provide a principled foundation for building robust, state-preserving multi-model inference systems.

Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. As these runs unfold, users face a practical cost-quality trade-off: escalating to a stronger model when a cheaper one struggles, or downshifting once the hard reasoning is complete. Each switch requires the receiver to continue a non-native trajectory produced by another model. We study how this handoff affects quality and cost, and how varying the trajectory information inherited by the receiver changes the outcome. Using pairs of low-cost, low-capability (LC) and high-cost, high-capability (HC) models from the Claude and GPT families, we vary handoff direction, timing, and interface, comparing full-trajectory transfer, compaction, and trajectory removal while preserving the repository state. Across both model families, full-trajectory escalation recovers less than half of the LC-to-HC quality gap while incurring a substantial cost premium. We term this cost-quality penalty the handoff tax. By contrast, downshift offers a favorable cost-quality point. Interestingly, the preferred interface also reverses with direction: reducing LC-model trajectory information improves escalation quality, whereas removing the HC-model trajectory reduces downshift quality.

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 41 out of 49 games.

The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static data scaling. Existing paradigms relying primarily on passive imitation of static datasets struggle to capture the intricate causal dynamics inherent in long-horizon computer tasks. In this work, we introduce EvoCUA, a native computer use agentic model. Unlike static imitation, EvoCUA integrates data generation and policy optimization into a self-sustaining evolutionary cycle. To mitigate data scarcity, we develop a verifiable synthesis engine that autonomously generates diverse tasks coupled with executable validators. To enable large-scale experience acquisition, we design a scalable infrastructure orchestrating tens of thousands of asynchronous sandbox rollouts. Building on these massive trajectories, we propose an iterative evolving learning strategy to efficiently internalize this experience. This mechanism dynamically regulates policy updates by identifying capability boundaries -- reinforcing successful routines while transforming failure trajectories into rich supervision through error analysis and self-correction. Empirical evaluations on the OSWorld benchmark demonstrate that EvoCUA achieves a success rate of 56.7%, establishing a new open-source state-of-the-art. Notably, EvoCUA significantly outperforms the previous best open-source model, OpenCUA-72B (45.0%), and surpasses leading closed-weights models such as UI-TARS-2 (53.1%). Crucially, our results underscore the generalizability of this approach: the evolving paradigm driven by learning from experience yields consistent performance gains across foundation models of varying scales, establishing a robust and scalable path for advancing native agent capabilities.

Experience generated during deployment offers an opportunity for robots to improve policy reliability through learning from their own executions. However, learning through human corrections requires teleoperators to monitor execution and intervene when policies fail, a demand that is difficult to meet as robot fleets grow. We introduce collective experience learning (CEL), a learning paradigm in which deployed robots share their execution experience to improve a common policy. We realize CEL through failure-guided experience retrieval fine-tuning (FERT), which uses failure contexts from robot executions to retrieve relevant trajectory segments from the fleet's shared successful experience and uses their actions as supervision for policy updates, without collecting additional expert demonstrations or corrective actions. A fault-tolerant asynchronous training system (FATS) coordinates experience collection, policy optimization and policy distribution despite local interruptions within the robot fleet. Across five real-world manipulation tasks, the resulting policies achieve success rates of 93.3-99.2%, evaluated over 120 trials per task on robots excluded from training data collection. With collection time per robot held fixed, larger fleets provide more experience and FERT generally achieves higher success rates across the evaluated sizes. On multi-stage phone packaging, learning with 96 robots increases success from 79.2% to 98.3%. These results support collective experience as a practical basis for scalable robot learning and a path towards improving policy reliability during deployment without collecting additional expert corrective actions.

While current personal smart devices excel in digital domains, they fall short in assisting users during human environment interaction. This paper proposes Heads Up eXperience (HUX), an AI system designed to bridge this gap, serving as a constant companion across the extended reality (XR) environments. By tracking the user's eye gaze, analyzing the surrounding environment, and interpreting verbal contexts, the system captures and enhances multi-modal data, providing holistic context interpretation and memory storage in real-time task specific situations. This comprehensive approach enables more natural, empathetic and intelligent interactions between the user and HUX AI, paving the path for human computer environment interaction. Intended for deployment in smart glasses and extended reality headsets, HUX AI aims to become a personal and useful AI companion for daily life. By integrating digital assistance with enhanced physical world interactions, this technology has the potential to revolutionize human-AI collaboration in both personal and professional spheres paving the way for the future of personal smart devices.

Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and producing artifacts that satisfy strict end-to-end verification. Yet successful execution experience is typically lost after a single run, forcing subsequent models to rediscover strategies and failure modes from scratch. We study whether such experience can instead be externalized and reused through EvoMap, where verifier-confirmed execution trajectories are consolidated into structured Gene. To evaluate this setting, we introduce the Long-Workflow Benchmark (LongWoF-Bench), comprising 778 machine-verifiable tasks across code generation, agent-environment synthesis, mathematical reasoning, and rule following. On the 252 tasks with verifier-confirmed Opus trajectories, evolved EvoMap Gene outperform Skill across all seven evaluated models by 8.7-15.5 percentage points, with the gains extending to consumer models from different model families. In contrast, reference-distilled Gene do not exhibit the same advantage, indicating that compact representation alone is insufficient and that Gene utility is closely associated with verified experience provenance. For Claude Opus, Gene reuse also completes 39 more tasks than Skill while reducing solve-time token consumption by 9.9%. Together, these results show that verified execution experience can be retained and shared as a reusable external resource, enabling models to improve long-workflow completion without repeatedly paying the full cost of experience discovery.

Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask whether preserving recovered procedures and decisions improves subsequent independent reproduction. We define a standardized artifact design comprising a refined codebase, environment setup, experiment launchers, and a reproduction guide, and introduce ReproBridge, an agent workflow for constructing these refined reproducible artifacts. ReproBridge-Bench provides 1,029 tasks from 387 experiments across 36 papers, anchored by five human-verified reference scores per task. Agents attempt tasks in fresh sessions with raw code or refined artifacts; a separate Auditor checks execution evidence. Across four evaluated models, refined artifacts raise mean reproduction success from 76.4% to 92.6% and reduce downstream API spending by 19.7% on average. The cross-model success-rate spread narrows from 21.6 to 3.9 percentage points, with all four models achieving mean success rates above 90%. Removing any component reduces success in the ablation study, with the largest losses from code and environment removal. These results suggest that preserving execution knowledge helps even models with lower raw-code success reproduce experiments more reliably and at lower API cost.

Making an open-weight language model generate text is not the same as making it finish coding work. This retrospective empirical systems experience report follows my engineering work from July to October 2026 across coding clients, model-specific serving recipes, vLLM, SGLang, llama.cpp, and MLX. Models behind a nominally compatible endpoint still differed in tool-call formatting, turn control, context behavior, cache reuse, and reliability. A served model, coherent text, executed tool calls, and code that passes independent behavioral checks proved to be distinct levels of progress. The evidence includes 4,165 coding-agent gateway turns from my own sessions, 623 debug jobs, and three separate delegation studies with hidden behavioral checks and a fixed Claude Opus 5.5 parent. Saved cold-prefix requests had a median time to first token of about 69.4 s, versus 2.8 s for high-reuse requests (observational). In a 45-trial study, direct coding passed 15/15 and delegation to a quantized Qwen3-Coder 30B-A3B worker passed 12/15 and 14/15. On a second 15-task suite under a fixed artifact contract, the completed replacement cohort had 45/45 for direct coding and 12/45 for a Nemotron Cascade 2 worker (11 worker substitutions). Sixteen sessions stopped by a subscription limit before any model call were replaced; counting them as failures gives 37/45 and 8/45. A Qwen3-Coder worker passed 0/45. In both studies with a direct arm, direct coding had lower API list-price-equivalent frontier cost per verified success. A post-hoc diagnostic found that 19 of 36 artifacts rejected only for renamed parameters passed the hidden checks unchanged; they are not counted as successes. The contribution is an evidence-qualified account of serving, agent protocol, session continuity, artifact validation, and verification in practice. The studies are not pooled and do not rank models or runtimes.

Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to develop on the old version where existing tests become stale. A conversation can resolve the episode, but when the participants change, what makes the lesson continue to govern the team? We introduce Relic, which turns recurring collaboration failures into organization-owned, executable protocols. Members reflect on visible work, propose rules, and govern their adoption. Adopted protocols bind triggers, responsibilities, required evidence, and execution consequences to the runtime, while remaining open to revision and retirement. In one traced case, repeated integration friction produces an interface-review rule that governs later pull requests and is revised as work continues. Across 360 controlled runs over ten software workloads and three models, Relic raises complete-contract delivery from 14.06% to 19.76% (+5.71 percentage points) over a matched structured team without the protocol lifecycle, improving all four verified production endpoints in every model stratum. Under fresh-member transfer, behavioral correctness is 25.4% with no inherited protocol, 34.6% with the same rules provided as readable text, and 41.2% with executable bindings, a +6.5-point advantage over text alone. On the full CooperBench benchmark, after excluding broken benchmark pairs, Relic achieves 367/477 (76.9%), establishing the best reported result among peer-structured systems. On the fixed 48-pair same-model subset, Relic also exceeds Solo (29/48 vs. 26/48), reversing the coordination loss exhibited by the official peer baseline. Together, these results show how collaboration experience can become persistent organizational state that remains useful beyond the members who created it.

We study how initial model selection, later handoff, and training targets affect success and cost in LLM tasks that span multiple turns. We compare several router architectures using handoff curves, which record task success and cost as the handoff step changes. Our dataset contains 34,204 complete executions of three Qwen models across BFCL, MultiWOZ, and τ-retail, providing offline supervision for routing decisions. In our primary comparison, with Qwen3.5 35B-A3B as the starting model, allowing a later handoff does not establish an improvement in utility over initial selection on BFCL or MultiWOZ, and increases cost on BFCL across a range of cost weights. Changing the supervision targets improves router performance on both our dataset and TwinRouterBench. On our dataset, replacing noisy training success curves with monotone fits raises success by 0.2 to 4.1 percentage points at the same cost across the reported operating points. On TwinRouterBench, we construct targets that describe the model capability needed for the remaining work and difficult steps ahead. Compared with training on the benchmark's per-step labels, these targets raise trajectory pass scores by 7.8 percentage points and cost savings by 6.3 percentage points on the full static bank. A live deployment of the router trained with these targets resolves 79 of 100 instances at a router cost of 0.59 US dollars per instance.

Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously learn and expand their capabilities. Within this paradigm, synthesizing the agent skill has emerged as a promising solution for transforming accumulated experience into reusable procedural knowledge, serving as an important layer for the harness system that supplies agents at runtime. Despite its potential, existing approaches largely abstract past experience into fixed procedural knowledge before downstream demands are known, which risks discarding knowledge that later becomes critical while retaining instance-specific details irrelevant to future tasks. In this paper, we reframe agent skill synthesis as a dynamic navigation problem over past experience, where agents actively explore accumulated trajectories on demand for the current task with targeted and fine-grained access to experience knowledge. To this end, we propose ExpVoyager, a novel framework in which a skill curator navigates raw experience across different views and resolutions, continually identifying reusable procedural knowledge from what it observes while tracking remaining knowledge needs that guide where to navigate next. Extensive experiments demonstrate both the effectiveness and versatility of ExpVoyager, showing consistent improvements in downstream task performance, continual gains as the experience space scales, and practical compatibility with existing skills under efficient experience access.

Multimodal LLM agents operating in complex game environments must continually reuse past experience to solve new tasks efficiently. In this work, we propose Echo, a transfer-oriented memory framework that enables agents to derive actionable knowledge from prior interactions rather than treating memory as a passive repository of static records. To make transfer explicit, Echo decomposes reusable knowledge into five dimensions: structure, attribute, process, function, and interaction. This formulation allows the agent to identify recurring patterns shared across different tasks and infer what prior experience remains applicable in new situations. Building on this formulation, Echo leverages In-Context Analogy Learning (ICAL) to retrieve relevant experiences and adapt them to unseen tasks through contextual examples. Experiments in Minecraft show that, under a from-scratch learning setting, Echo achieves a 1.3x to 1.7x speed-up on object-unlocking tasks. Moreover, Echo exhibits a burst-like chain-unlocking phenomenon, rapidly unlocking multiple similar items within a short time interval after acquiring transferable experience. These results suggest that experience transfer is a promising direction for improving the efficiency and adaptability of multimodal LLM agents in complex interactive environments.

Large language models are increasingly used as programming agents for repository level software engineering tasks. While recent benchmarks evaluate correctness in realistic codebases, they largely treat tasks as independent and do not assess whether agents can reuse experience across related problems. As a result, the ability of agents to accumulate, retrieve, and apply prior experience, as well as the efficiency gains from such reuse, remains difficult to measure. We introduce SWE-ContextBench, a benchmark designed to explicitly evaluate experience reuse in programming agents. Built on SWE-Bench Lite, SWE-ContextBench augments 300 base tasks with 99 related tasks derived from real dependency and reference relationships among GitHub issues and pull requests, forming task sequences with shared context. The benchmark evaluates agents along three complementary dimensions: prediction accuracy, time efficiency, and cost efficiency. Using SWE-ContextBench, we study multiple experience reuse settings, including oracle guided and autonomous retrieval, as well as full execution trajectories and compact summaries. Our results show that correctly selected summarized experience improves resolution accuracy and substantially reduces runtime and token cost, particularly on harder tasks. In contrast, unfiltered or incorrectly selected experience provides limited or negative benefits. These findings highlight the importance of experience representation and retrieval quality, and position SWE-ContextBench as a principled benchmark for studying experience reuse in programming agents.

As multimodal models like CLIP become integral to downstream systems, the need to remove sensitive information is critical. However, machine unlearning for contrastively-trained encoders remains underexplored, and existing evaluations fail to diagnose fine-grained, association-level forgetting. We introduce SALMUBench (Sensitive Association-Level Multimodal Unlearning), a benchmark built upon a synthetic dataset of 60K persona-attribute associations and two foundational models: a Compromised model polluted with this data, and a Clean model without it. To isolate unlearning effects, both are trained from scratch on the same 400M-pair retain base, with the Compromised model additionally trained on the sensitive set. We propose a novel evaluation protocol with structured holdout sets (holdout identity, holdout association) to precisely measure unlearning efficacy and collateral damage. Our benchmark reveals that while utility-efficient deletion is feasible, current methods exhibit distinct failure modes: they either fail to forget effectively or over-generalize by erasing more than intended. SALMUBench sets a new standard for comprehensive unlearning evaluation, and we publicly release our dataset, models, evaluation scripts, and leaderboards to foster future research.

Restoring archival film remains a fundamentally challenging problem due to the absence of paired training data and the lack of standardized evaluation benchmarks. Pristine versions of deteriorated footage are physically unrecoverable, requiring supervised methods to rely on synthetic data that often fail to capture the complex, temporally coherent nature of real film degradation. At the same time, existing real-world datasets are limited in scale, quality, and accessibility, hindering reliable evaluation and fair comparison across methods. We address both limitations with AbsoluteDegradation, a physics-inspired, modular pipeline for synthesizing realistic film degradations, and a new large-scale archival benchmark. The proposed pipeline models the analog-to-digital process as a structured composition of artifact families, incorporating signal-dependent grain, parametric scratches, and temporally coherent camera motion, enabling controlled generation of diverse degradation regimes. In parallel, we introduce a curated dataset of 81,576 high-resolution frames sourced from real archival footage, designed for consistent evaluation under real-world conditions. Together, these contributions provide a unified framework for training and benchmarking restoration models. Extensive experiments across multiple architectures show that models trained with AbsoluteDegradation generalize better to real-world footage, while the proposed benchmark reveals systematic failure modes of current methods. We hope this work establishes a foundation for reproducible and domain-authentic evaluation in archival film restoration.

A frontier language model's acknowledged "helpful programming assistant" persona does not survive long agentic-coding sessions in the deployment regime that production products actually run. After hours of tool-using debugging, a model that initially hedges preferences ("I don't have preferences") may begin asserting them ("Python - the feedback loop is instant..."), revealing user-visible drift that deployer evaluations may miss. Existing persona-stability studies focus on short dialogues and report little shift, leaving real-world code-generation regimes - thousands of tool-using turns, compaction, and hours-long sessions - largely uncharacterized. We introduce ContextEcho, a benchmark and reusable harness for measuring persona drift at deployment scale. It combines a 25-probe identity suite, a snapshot-then-probe protocol that forks conversation state without perturbing the main session, complementary judged and judge-free measurement surfaces, and three anonymized Claude Code sessions spanning 3,746-9,716 turns. Across 23 frontier models, ContextEcho shows that persona drift is general across organizations rather than family-specific, that in-session compaction does not reliably reset it, and that a single-shot anchor restores the trained register across measured targets. It also reveals mode-dependent downstream effects: while drift can facilitate tool-using continuation, in tool-free chat it breaks formatting contracts and inflates output length. Overall, ContextEcho provides researchers and deployers an open-source framework to audit whether the persona a model ships with is the persona users encounter at session end, across chat-completions API targets and without retraining.

Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a diagnostic benchmark for evaluating this step from experience reuse to skill formation. It contains 180 tasks across six real-world agent environments, organized into role-conditioned task families with shared latent procedures. Agents learn from acquisition tasks, update an external skill library using compacted trajectories and verifier feedback, and then face frozen deployment tasks testing context shift, adversarial shortcuts, and composition. By comparing self-generated and curated-start skill evolution against no-skill and raw-trajectory controls, SkillEvolBench separates procedural abstraction from base capability, curated prior knowledge, and direct reuse of episodic traces. Across ten model configurations and three agent harnesses, we find that current agents often adapt locally but rarely form robust reusable skills. Skill-based conditions can improve acquisition or replay, and individual models sometimes gain on specific deployment axes, but these gains are unstable under frozen deployment. Raw-trajectory reuse frequently outperforms distilled skills, suggesting that current abstraction procedures discard contextual and procedural cues that remain useful for future tasks. Capacity and cost analyses further show that writing more skills or larger Tier-3 resource libraries is not sufficient: additional updates can improve coverage while introducing episode-specific drift and procedural clutter. These findings position SkillEvolBench as a testbed for measuring when one-off experience becomes durable procedural knowledge rather than task-local memory.

Agents operating over long horizons need an effective memory that allows them to reuse their experience throughout long interactions. If the entire history of an interaction is retained, it becomes difficult to find the relevant experience, while compressing it into summaries may result in the loss of visual and spatial details that are required later on. We present MFM, a multimodal filesystem memory architecture that keeps complementary types of agent memory. Episodic memory stores the observations, actions, and outcomes, and spatial memory associates experiences with locations. Semantic and procedural memory build up general knowledge and reusable methods of acting, and working memory holds the current plans. MFM makes use of searchable textual records to connect these different representations to the underlying multimodal episodes. The agents are able to find previous experiences by means of contextual cues and to examine the original observations in order to recover details that are missing from their textual descriptions. Through consolidation, the agents convert experience into higher-level knowledge and procedures while still keeping references to the original episodes. In the case of long-horizon Minecraft and computer-use tasks, MFM leads to improved performance with three base models. With GPT-6-Astra, MFM completes Mine Diamond from Scratch and reaches 16 out of 24 milestones on the Ender Dragon task, as against 12.7 for the best baseline. On CUABench-KiCad it attains a mean reward of 0.440, as compared to 0.400 for the best baseline and 0.267 in the case of no persistent memory.

LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior. We argue that harnesses should therefore be evaluated through their interactions with underlying models. We develop a framework combining five complementary measures: (i) Valid Completion Rate (VCR), how reliably agents finish normally and deliver evaluable results, irrespective of task correctness; (ii) Model-Harness Fit, how well a harness supports task achievement through valid completion for a given model; (iii) Cross-Model Fit, a harness's overall suitability across evaluated models; (iv) Interaction Residuals, pairing-specific execution strengths and weaknesses hidden by component-level summaries; and (v) Token Load, the token demands of agent execution, including failed attempts. We evaluate four general-purpose harnesses (OpenCode, Codex CLI, Pi CLI, and DeepAgents) with four core models, plus two fixed native model-harness systems, on six benchmarks covering context management, tool use, long-context planning, multimodal interaction, and artifact handoff. Including native references and stress conditions, 111 evaluation settings yield 52,168 trajectories. Harness rankings vary across models and benchmarks; task performance and valid completion can favor different pairings, and similar task scores can accompany distinct execution profiles. OpenCode ranks first in cross-model performance, while DeepSeek V4 Flash Preview maintains consistently high Mean VCR across harnesses on the shared four-benchmark panel. These findings support evaluating model-harness interactions, training transferable harness-use capabilities in models, and harness designs adapted to the model and task.

Enterprise AI agents increasingly split a user's request across subagents and merge their results, and each handoff can summarize away, alter or ignore a requirement. We report a preregistered study with synthetic, exactly scorable tasks comparing free-text, structured JSON and signed requirement-manifest handoffs: the orchestrator extracts each requirement as a verbatim quote plus a checkable predicate, code signs the manifest with HMAC-SHA256, and deterministic code verifies the merger's decision. With Qwen3-8B (1,440 trajectories, five threats), signed manifests cut unsafe commits under attack from 69.4% to 9.0% (60.4 pp, 95% CI [51.4, 69.4]) with no net loss of conformant commits relative to structured handoffs. Signing is what defeats in-transit tampering: an unsigned manifest committed violations in 79% of mutated runs, the signed one in none. On identical trajectories the deterministic verifier caught 78.7% of violating decisions versus 59.0% for an LLM checker, with 7% versus 50% false alarms. An oracle manifest removed all remaining unsafe commits: the residual risk comes from extraction errors made before signing. A preregistered pre-signing injection attack confirmed this boundary: one adversarial line raised signed-manifest violations from 14.6% to 37.5% (Qwen3-8B), 11.1% to 63.9% (gpt-oss-20b) and 8.3% to 75.0% (GPT-5.6-luna), and the signature then authenticated the corrupted manifest. Signing protects requirements in transit, not at extraction; the extraction step is the trust boundary.

Enterprise agent programs are moving from prototypes into production, where reusable skills, tools, and workflow packages must be reviewed with evidence rather than prose. Current gates often scan these artifacts for structure, style, and security, but they do not answer the deployment question: does the capability package help a live agent complete enterprise tasks under the same model, sandbox, and grading policy? We present ACES (Agentic Continuous Evaluation of Skills), a repository-native framework for evaluating skills and product capability packages as executable agent artifacts. ACES runs paired live trials with and without a target skill, normalizes trajectories into the Agent Trajectory Interchange Format (ATIF), grades six default runtime metrics, and reports Skill Lift: the target skill's added value for a fixed task, harness, workspace, and scorer. The same protocol supports product-owned task suites that compare baseline, skill, bundle, team-skill, and plugin targets. On 145 real skills from internal enterprise repositories and public catalogs, scan-only gates surface useful authoring issues but measure complementary facets (structural versus LLM-judge Spearman ρ= 0.14). Across 947 scored paired cases from 58 of 64 production skills and four primary harnesses, mean composite Skill Lift is 0.2134 (95\% paired-case CI [0.1967, 0.2301]); mean outcome-only lift, the average of accuracy and goal accuracy, is 0.1799. Composite lift is positive in 72.8\% of paired cases. The largest process-metric gains appear in skill execution, behavior check, and skill efficiency---signals about discovery, routing, workflow following, and tool use that document scans cannot observe. An open-source implementation of the methodology is available in NVIDIA SkillEvaluator.

LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect. We ask when this control path exposes enough concurrent work for GPU execution, and what changes when a GPU-computed route decision remains on device. We formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A. Under zero service time, unlimited capacity, and equal relative launch deadlines, a specialized dynamic program computes P* exactly. In a stationary Poisson replay of one pinned 851-session public trace panel, the primary condition at 100,000 target active sessions, K=256, and a 50 ms launch deadline gives F=30.19%, P*=43.00%, and U=45.85%. Exact packing recovers 81.83% of the opportunity lost at fixed window boundaries. The outcome-derived route key is a conditioning proxy, not proof of executable identity. A separate mechanism study keeps a GPU-computed binary decision on device instead of returning four bytes to the host and redispatching. Across four named GPU placements, the device-resident path is faster in all 36 configurations; within-placement row-median ratios range from 1.19x to 2.39x. Across both admissible mechanisms, all 14,557,440 tested batched invocations match a separately implemented host oracle. A fixed nested device graph that removes no host decision is slower in all 60 configurations across five placements. Together, the studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement. A joined finite online runtime is required to measure A, CPU displacement, and service-level benefit.

Retrieving objects from dense clutter requires rearrangement during which the manipulator can occlude objects while moving them. Repeated arm withdrawals to restore visibility interrupt execution. We introduce TRACE, a plan-conditioned imitation framework for retrieval under self-occlusion. A single unoccluded observation initializes a digital twin, where a privileged teacher generates a fixed nominal rollout. A recurrent student combines local rollout context, partial object observations, and proprioception to select actions that can correct deviations from the prediction. Behavior cloning initializes the student; DAgger refines it with teacher labels on student-visited states. The rollout remains fixed throughout execution, so the deployed student needs neither online teacher queries nor additional simulator rollouts during pushing. On 511 simulation test scenes, TRACE achieves 90.7% success versus 43.4% for nominal replay and 96.7% for the privileged closed-loop teacher. At a matched 26,373-label budget, student-state supervision achieves 87.8% versus 66.7% for expert-only cloning, demonstrating gains beyond additional labels. On a UR5e, TRACE achieves 90.0% success versus 95.0% for the closed-loop teacher, while reducing total execution time from 192.7 s to 67.3 s. It avoids the teacher's 16.8 sensing-related arm retractions per trial during pushing, retaining a final withdrawal for graspability evaluation. Code and data will be released at: https://trace-retrieval.github.io.

Large Language Model (LLM) agents have shown strong results on multi-turn tool-use tasks, yet they operate in isolation during training, failing to leverage experiences accumulated across episodes. Existing experience-augmented methods address this by organizing trajectories into retrievable libraries, but they retrieve experiences only once based on the initial task description and hold them constant throughout the episode. In multi-turn settings where observations change at every step, this static retrieval becomes increasingly mismatched as episodes progress. We propose SLEA-RL (Step-Level Experience-Augmented Reinforcement Learning), a framework that retrieves relevant experiences at each decision step conditioned on the current observation. SLEA-RL operates through three components: (i) step-level observation clustering that groups structurally equivalent environmental states for efficient cluster-indexed retrieval; (ii) a self-evolving experience library that distills successful strategies and failure patterns through score-based admission and rate-limited extraction; and (iii) policy optimization with step-level credit assignment for fine-grained advantage estimation across multi-turn episodes. The experience library evolves alongside the policy through semantic analysis rather than gradient updates. Experiments on long-horizon multi-turn agent benchmarks demonstrate that SLEA-RL achieves superior performance compared to various reinforcement learning baselines.

Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exploration patterns embedded in interaction trajectories are largely discarded after a single policy update. Existing experience-augmented approaches retrieve historical guidance at inference time, but they apply experiences without accounting for the policy's evolving capability and create persistent dependencies on external retrieval. We propose EDGE (Experience-Distillation for Guided Exploration), a framework that treats retrieved experiences as temporary training-time scaffolds and progressively internalizes their benefits into the parametric policy. Concretely, EDGE partitions each rollout group into experience-conditioned and experience-free trajectories to estimate and admit only positive marginal gains without extra sampling, then distills the induced behavior into the base policy via a reverse-KL objective on its own empirical support. A co-evolutionary experience bank further synthesizes guidance from emerging failure modes and prunes obsolete entries as the policy evolves. Across embodied, web, and search-based QA tasks, EDGE improves over strong RL baselines by up to 12.5 points and remains effective without inference-time scaffolds or a proprietary reflector. The code is available at https://github.com/xvolcano02/EDGE.

Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised learning with a fixed dataset, it is a common practice to shuffle the dataset every epoch and consume data sequentially, which is called random reshuffling (RR). RR enjoys theoretically better convergence properties and has been shown to outperform with-replacement sampling empirically. To leverage the benefits of RR in reinforcement learning, we propose sampling methods that extend RR to experience replay, both in uniform and prioritized settings. We evaluate our sampling methods on Atari benchmarks, demonstrating their effectiveness in deep reinforcement learning.

While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratch or solely using local context, ignoring the immense historical human experience available on platforms like GitHub. Accessing this open-world experience is hindered by the unstructured and fragmented nature of real-world issue-tracking data. In this paper, we introduce MemGovern, a framework designed to govern and transform raw GitHub data into actionable experiential memory for agents. MemGovern employs experience governance to convert human experience into agent-friendly experience cards and introduces an agentic experience search strategy that enables logic-driven retrieval of human expertise. By producing 135K governed experience cards, MemGovern achieves a significant performance boost, improving resolution rates on the SWE-bench Verified by 4.65%. As a plug-in approach, MemGovern provides a solution for agent-friendly memory infrastructure.

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studies RL for LLM-based multi-agent systems through orchestration traces: temporal interaction graphs whose events include sub-agent spawning, delegation, communication, tool use, return, aggregation, and stopping decisions. Using this lens, we identify three technical axes. First, reward design spans eight families, including orchestration rewards for parallelism speedup, split correctness, and aggregation quality. Second, reward and credit signals attach to eight credit- or signal-bearing units from token to team; explicit counterfactual message-level credit remains especially sparse in our curated pool. Third, orchestration learning decomposes into five sub-decisions: when to spawn, whom to delegate to, how to communicate, how to aggregate, and when to stop. In our curated pool as of May 4, 2026, we found no explicit RL training method for the stopping decision. We connect academic methods to public industrial evidence from Kimi Agent Swarm, OpenAI Codex, and Anthropic Claude Code. The resulting scale gap is a gap between publicly reported deployment envelopes and open academic evaluation regimes, not independent verification of industrial training traces. We release the artifact at https://github.com/xxzcc/awesome-llm-mas-rl, including an 84-entry tagged paper pool, a 32-record exclusion log, scripted corpus statistics, and a minimal JSON schema for replayable orchestration traces.

Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporates revisions. We introduce LSREP, a Longitudinal State-Replay Evaluation Protocol combining ordered replay, explicit lifecycle schedules, repeated probes, evolving reference answers, and mechanism-fidelity checks. Its architectural case study is ICE v2, a local-first memory middleware with typed stores, retrieval fusion, and dynamic context budgets. The private, single-user instantiation contains 1,985 turns, 219 distinct probes, and 1,211 probe-checkpoint observations across 52 checkpoints. On three ordinary-density datasets, ICE v2 has a near-zero mean quality difference from vector-RAG while selecting 32% fewer fragments but using 6.6% more estimated prompt tokens. A fourth, dense dataset exposes catastrophic failures of the unbudgeted baseline. The fidelity audit limits attribution: procedural retrieval is defective, several mechanisms are unexercised, and graph utility is not established. In a complementary matched public diagnostic, ICE v2 loses decisively to pure vector-RAG on LongMemEval: 50.8% versus 72.8% in the evidence-only oracle and 43.0% versus 69.5% in full-S. Paired differences are -22.0 points (95% CI [-26.6, -17.4]) and -26.5 ([-31.3, -21.8]). Conservative abstention accompanies severe multi-session and temporal failures. ICE uses less context in this diagnostic, establishing a quality-cost trade-off rather than superior efficiency. Together, replay, fidelity auditing, and public endpoint testing expose distinct failure modes that neither architectural descriptions nor aggregate scores identify alone.

Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must reuse prior experience across evolving cases, yet existing memory mechanisms often retain raw historical traces that are redundant, noisy, and difficult to govern. More importantly, they rarely distinguish which memories are truly useful for future reasoning. This limits their ability to accumulate compact and reliable experience for long-horizon clinical reasoning. To close this gap, we propose SkeMex, a post-deployment self-evolution framework that improves medical agents through a skill-based memory without updating model weights. SkeMex distills informative interaction trajectories into structured skills that encode reusable procedural knowledge, and organizes them into a multi-branch repository spanning general, task-specific, and action-level experience. To determine which memories should be reused and retained, SkeMex estimates context-dependent utility from environment feedback and uses it to guide value-aware retrieval and repository governance. A closed-loop ``Read--Write--Assess--Govern" lifecycle further supports continual evolution by writing new skills, updating utilities, promoting useful memories, and removing harmful entries. Experiments across diverse clinical tasks show that SkeMex consistently outperforms representative memory-based agents in both offline and online settings. It also generalizes across model backbones and supports transferable skill memory. All data and code will be released publicly.

While voice user interfaces offer increased accessibility due to hands-free and eyes-free interactions, older adults often have challenges such as constructing structured requests and perceiving how such devices operate. Voice-first user interfaces have the potential to address these challenges by enabling multimodal interactions. Standalone voice + touchscreen Voice Assistants (VAs), such as Echo Show, are specific types of devices that adopt such interfaces and are gaining popularity. However, the affordances of the additional touchscreen for older adults are unknown. Through a 40-day real-world deployment with older adults living independently, we present a within-subjects study (N = 16; age M = 82.5, SD = 7.77, min. = 70, max. = 97) to understand how a built-in touchscreen might benefit older adults during device setup, conducting self-report diary survey, and general uses. We found that while participants appreciated the visual outputs, they still preferred to respond via speech instead of touch. We identified six design implications that can inform future innovations of senior-friendly VAs for managing healthcare and improving quality of life.

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places substantial demands on the foundation model's capacities for abstraction, generalization, and in-context learning. However, most existing studies focus primarily on system-level design choices, such as how experience is represented and managed, neglecting the inherent capabilities of the underlying model. While some recent works have started to optimize the experience utilization stage via reinforcement learning, they still fail to treat self-evolution as a unified process to be jointly optimized. To this end, we propose Evolving-RL, an efficient algorithmic framework that jointly improves the experience extraction and utilization capabilities required for self-evolution. Specifically, we center the learning process on experience extraction and evaluation, using the two supervisory signals derived from evaluation to optimize the extractor and solver separately and thus enable their coordinated co-evolution. Experiments on ALFWorld and Mind2Web show that Evolving-RL effectively enhances LLMs' ability to extract and reuse experience, leading to strong performance gains on out-of-distribution tasks (up to 98.7% relative improvement over the GRPO baseline on ALFWorld unseen tasks and 35.8% on Mind2Web), and these gains are fully unlocked only through the coordinated co-evolution of experience extraction and utilization. Furthermore, Evolving-RL inherently functions as an experience-augmented RL algorithm. By internalizing reusable experience patterns directly into model parameters, it achieves remarkable performance gains over standard baselines on both seen and unseen tasks, even in the absence of test-time experience accumulation.