new

Get trending papers in your email inbox!

Subscribe

Daily Papers

byAK and the research community

Nov 17

NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities

We introduce NemotronLabs VoiceChat, an open full-duplex speech-to-speech model with native tool-calling capabilities. NemotronLabs VoiceChat combines a streaming speech encoder and decoder-only language model with parallel specialized output streams for agent text and structured function calls, an auxiliary RNN-T branch for incremental user transcription, and a streaming TTS decoder. This design enables the model to listen, transcribe, reason, invoke tools, and speak within a unified streaming architecture while preserving the temporal behavior required for natural conversation. On Full-Duplex-Bench 1.0, NemotronLabs VoiceChat achieves the lowest pause-handling takeover rates among evaluated open-weight systems, 100\% takeover following user interruptions, and a 4.33/5 post-interruption response-quality score. On Full-Duplex-Bench 1.5, it resumes its response after user backchannels in 93\% of cases. NemotronLabs VoiceChat obtains a 55.1 normalized average on VoiceBench and, on Full-Duplex-Bench 3.0 (FDB 3.0), achieves 82.5\% tool-selection F1, while argument accuracy and end-to-end tool execution remain areas for improvement. These results demonstrate that full-duplex interaction, speech recognition and generation, general language capabilities, and external tool use can be integrated in a single open speech-to-speech model without sacrificing real-time conversational behavior.

  • 49 authors
·
Sep 17 1

RLPF: Reinforcement Learning from Performance Feedback for Code Generation

Code models are increasingly trained with execution feedback, but most training signals still stop at correctness. This leaves an important gap for systems code: two programs can pass the same tests while differing greatly in runtime. We study how to train code agents to prefer faster correct implementations, rather than treating efficiency only as an evaluation metric. The key difficulty is that runtime is a fragile reward. It is meaningful only after a program is correct, varies across tasks, and gives little guidance when most sampled programs fail to compile or run. We propose RLPF, reinforcement learning from performance feedback, which turns execution outcomes into a staged reward. Failed programs are ordered by execution progress, while correct programs are ranked by their relative improvement from the baseline toward the expert reference. This gives useful feedback before correctness and performance-sensitive feedback after correctness. Fine-tuning Qwen3-32B with RLPF on PerfCodeBench raises correct-and-runnable solutions from 11.1% to 54.6% and improves relative efficiency from 8.1% to 38.6%. The trained model becomes competitive with stronger open-weight systems, and its optimization behavior transfers modestly to EffiBench-X. Additional studies show that model-generated references provide useful but weaker supervision, and that the full composite reward is more reliable than correctness-only or runtime-only baselines. These results suggest that code agents can be trained not only to pass tests, but also to optimize the programs they write.

  • 12 authors
·
Jul 28

ParseBench-2: Severity-Aware Evaluation of Document Parsing

Document-parsing metrics can give high scores to outputs that change important facts and penalize changes that preserve meaning. People can often judge these consequences more easily than they can design a metric to measure them. We introduce a method for developing parsing metrics from severity policies that specify how each error type should affect the score. We express these policies through test scenarios that specify how a metric should behave. We then optimize the metric implementations against these fixed expectations, using coding agents to refine comparison rules, error detectors and weights under human review. This makes stated human priorities an explicit objective of metric design. We apply this method in ParseBench-2, a comprehensive document-parsing benchmark that combines broad capability coverage with metrics calibrated to error severity. It covers 4,317 pages across six dimensions of parsing quality: text, formatting, tables, charts, visual grounding, and forms. We use detailed annotations and targeted difficult cases to check for changed facts, broken structural relationships, and missing content. We take the lower of a parsing score that measures content recovery and a severity cap that penalizes detected errors, so recovering most of a page cannot hide a serious error. Across six severity test suites, our metrics more closely match the expert judgments expressed by the scenario targets than existing metrics and penalize at most 3.4% of the tested benign variations. We conduct a comprehensive evaluation spanning frontier vision-language models, specialized document parsers and open-weight systems, comparing their overall rankings, performance across parsing capabilities and tradeoffs between accuracy and cost.

  • 8 authors
·
Nov 11

Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena

A robot generalist must interpret a scene, act on it, and satisfy every condition of a task. How far do frontier vision-language models (VLMs) meet these demands? We introduce Embodied Agent Arena, evaluating ten VLM agents across Geometry, Spatial Reasoning, Affordance, Task Planning, and Manipulation. Its 1,000 cases combine 32 established sources with GeoProbe, our 168-case benchmark for camera, motion, depth, and scale estimation. A minimal harness leaves task decisions to the model through source-native interfaces. Closed-weight models lead all five domains, whereas open-weight VLMs show useful spatial reasoning but substantially lower planning and manipulation success. Beneath these averages, similar geometric errors conceal different scale and shape distortions, and valid region estimates need not identify usable action points. During execution, agents can achieve early subgoals yet lose object control, bind an action to the wrong receiving region, or stop before the required physical state holds. Additional computation does not uniformly resolve these failures: code repair can restore execution without completing the task, while self-review can reverse correct judgments. Failure costs also differ: the strongest planners concentrate failed-token expenditure in prolonged body-control tasks, whereas other models fail broadly across procedures. Matched traces show how successful recovery uses feedback to restore a missing prerequisite and advance the remaining task.

  • 10 authors
·
Oct 22 2

Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge

We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (NeMo Arabic ASR, an OpenAI-compatible LLM endpoint, self-hosted TTS) and a deterministic multi-source retrieval layer routed across six Model Context Protocol servers, we report three things a research prototype typically lacks. First, a released family of fine-tuned Arabic Islamic model artifacts: an efficient tool-routing LLM (Muslim-6B-PRO, 5.94B parameters) and a Modern Standard Arabic TTS model (Fasih-TTS-V1) that ranks 5th of 17 overall and 2nd of 11 open-weight systems on the community-voted Arabic TTS Arena for MSA. Second, an account and metering layer - a free per-account turn allowance, capacity-aware refusal, and email verification deferred to the point it actually matters - that turns an open demo into an operable, abuse-resistant product. Third, a three-layer observability stack (liveness, error reporting, product analytics) built specifically around the system's characteristic failure mode: a GPU-bound agent host going silent while the web tier keeps serving normally. We report real, measured latency and accuracy figures (98.4% recitation-validation accuracy on 124 cases; end-to-end voice latency of 0.9-1.7s) and discuss the concrete engineering trade-offs and limitations of running an Islamic-knowledge voice product in production.

  • 1 authors
·
Sep 24

VeriSpoof: Beyond Real or Fake with One Audio LLM

A speech deepfake detector estimates whether a recording is synthetic, but a forensic analyst also asks which system produced it, whether recordings share a source, and what evidence supports each conclusion. We present VeriSpoof, an audio language model that unifies five tasks with shared weights: deepfake detection, generator attribution (generator, acoustic model and vocoder), recording-condition analysis, synthesized-span localisation, and source verification. Each decision is supported by grounded rationales whose statements can be independently verified. Answers are scored by sentence likelihood, allowing detection and source verification to be thresholded without separate heads. Rationale statements can be checked against waveform measurements, span labels, or generator metadata. Counterfactual examples train decisions to follow the stated evidence. Across the 14 Speech-DF-Arena test sets, VeriSpoof-Plus achieves 2.14% pooled EER, ranking third of 28 systems and first among open-weight systems. VeriSpoof-Base, trained only on official training splits of eight corpora, achieves 4.43% EER, less than half that of the next open-weight detector. With the same weights, VeriSpoof-Plus verifies whether recordings from generators unseen in training share a source at 6.2% EER. Controlled studies show that the audio representation governs detection, the LLM governs recording comparison, and source supervision is necessary for neural-codec fakes. Statement-checkable rationales catch partial fakes missed by one-step answers (99.6% vs. 78.4% on PartialEdit) and determine decisions under edits unseen in training (99.5%). Training updates only 29.7M of 2.85B parameters, fitting a single 24 GB GPU with gradient checkpointing. We release both models, inference code, a demo, and VeriSpoof-Bench, the evaluation suite covering these questions.

Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or activations. Currently, there is not yet a robust science of open-weight model risk management. Existing safety fine-tuning methods and other post-training techniques have struggled to make LLMs resistant to more than a few dozen steps of adversarial fine-tuning. In this paper, we investigate whether filtering text about dual-use topics from training data can prevent unwanted capabilities and serve as a more tamper-resistant safeguard. We introduce a multi-stage pipeline for scalable data filtering and show that it offers a tractable and effective method for minimizing biothreat proxy knowledge in LLMs. We pretrain multiple 6.9B-parameter models from scratch and find that they exhibit substantial resistance to adversarial fine-tuning attacks on up to 10,000 steps and 300M tokens of biothreat-related text -- outperforming existing post-training baselines by over an order of magnitude -- with no observed degradation to unrelated capabilities. However, while filtered models lack internalized dangerous knowledge, we find that they can still leverage such information when it is provided in context (e.g., via search tool augmentation), demonstrating a need for a defense-in-depth approach. Overall, these findings help to establish pretraining data curation as a promising layer of defense for open-weight AI systems.

  • 10 authors
·
Aug 8, 2025 2

6G-Bench: An Open Benchmark for Semantic Communication and Network-Level Reasoning with Foundation Models in AI-Native 6G Networks

This paper introduces 6G-Bench, an open benchmark for evaluating semantic communication and network-level reasoning in AI-native 6G networks. 6G-Bench defines a taxonomy of 30 decision-making tasks (T1--T30) extracted from ongoing 6G and AI-agent standardization activities in 3GPP, IETF, ETSI, ITU-T, and the O-RAN Alliance, and organizes them into five standardization-aligned capability categories. Starting from 113,475 scenarios, we generate a balanced pool of 10,000 very-hard multiple-choice questions using task-conditioned prompts that enforce multi-step quantitative reasoning under uncertainty and worst-case regret minimization over multi-turn horizons. After automated filtering and expert human validation, 3,722 questions are retained as a high-confidence evaluation set, while the full pool is released to support training and fine-tuning of 6G-specialized models. Using 6G-Bench, we evaluate 22 foundation models spanning dense and mixture-of-experts architectures, short- and long-context designs (up to 1M tokens), and both open-weight and proprietary systems. Across models, deterministic single-shot accuracy (pass@1) spans a wide range from 0.22 to 0.82, highlighting substantial variation in semantic reasoning capability. Leading models achieve intent and policy reasoning accuracy in the range 0.87--0.89, while selective robustness analysis on reasoning-intensive tasks shows pass@5 values ranging from 0.20 to 0.91. To support open science and reproducibility, we release the 6G-Bench dataset on GitHub: https://github.com/maferrag/6G-Bench

  • 3 authors
·
Feb 9

State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning

Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables parameter-efficient reasoning in continuous latent space through an FFN-driven nonlinear recurrence at each decoder layer, where latent states are streamed horizontally across the full sequence via a learned blend. This same mechanism supports continuous latent deliberation per position at inference time, dedicating additional FLOPs to exploring abstract reasoning before committing to a token. A two-pass parallel training procedure resolves the sequential dependency of the recurrence to allow compute-efficient training. Hidden state analysis shows the state stream facilitates reasoning through exploration of distinct semantic basins in continuous latent space, where transitions at content-dependent positions move the model into a substantially different Bayesian posterior, directly influencing the latent space at future positions. We also find, via a learned probe, that at the first generated token position, the latent state already predicts whether the eventual answer will survive or break under additional latent computation for every subsequent position. Co-trained into an existing 27B backbone using only a small dataset of GSM8K examples, the SST delivers a +15.15 point gain over a fine-tuning-matched baseline on out-of-distribution GPQA-Diamond and cuts that same baseline's remaining GSM8K errors by 46%, together showing that the reasoning improvement is attributable to the architectural mechanism rather than scale or training data. On GPQA-Diamond, the resulting 27B SST also achieves higher accuracy than several larger open-weight and proprietary systems, including open-weight models up to 25 times larger.

  • 1 authors
·
Apr 29

Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?

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.

  • 1 authors
·
Oct 24 7

Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their interaction under joint deployment conditions remains insufficiently understood. This paper reports a reproducible phenomenon observed in a production Agent system: when Tool Calling and JSON Schema constraints are simultaneously enabled, multiple open-weight models cease invoking tools despite maintaining high schema compliance. We refer to this behavior as Tool Suppression. Through controlled experiments across multiple model families and deployment settings, we consistently reproduce Tool Suppression under joint constraints, while tool execution and schema compliance remain functional when evaluated independently. Further analysis reveals that JSON Schema constraints are compiled into grammar-based token masks, causing tool-call tokens to become unreachable during decoding. This provides an implementation-level explanation for the observed behavior. To interpret the phenomenon, we formulate the Constraint Priority Inversion (CPI) hypothesis, which suggests that schema satisfaction may dominate action-selection behavior under multiple simultaneous constraints. We present CPI as a behavioral hypothesis consistent with the observed evidence rather than a verified internal mechanism. To mitigate the problem, we propose Transparent Two-Pass Execution, an inference-time strategy that decouples tool execution from schema-constrained response generation. Experimental results show that this approach restores tool invocation while preserving structured output guarantees without requiring model retraining. These findings suggest that evaluating tool use and structured output separately may overlook important reliability issues in production Agent systems. Code, data, and docs will be released at https://github.com/Fzsama/Constrain-Tax-26-06.git.

  • 3 authors
·
Jun 23 3

Crypto Accounting Bench: Evaluating Frontier and Open-Weight Models on Crypto-Asset Accounting Tasks

We introduce Crypto Accounting Bench (CAB), a benchmark for assessing whether frontier and open-weight language models can reconstruct the complete journal entry that an organization actually posted for a crypto-asset transaction. CAB contains 118 evaluation tasks drawn from 7 pseudonymized organizations. Each task combines transaction mechanics, asset quantities and base-currency values, wallet and legal-entity context, counterparty evidence, related transaction legs, recurrence, tax-lot evidence, and the organization's complete chart of accounts. The target is a balanced structured entry with every required account, side, amount, currency, and full-precision asset quantity. We evaluate 12 models spanning proprietary frontier systems and open-weight releases over 3 independent attempts per task, producing 4,248 trajectories. We report 3 metrics: Mean Score, Best@3, and Pass@3. Pass@3 is the fraction of tasks with at least 1 of 3 attempts that satisfies every rubric criterion and required gate. The leading model reaches 77.43% Mean Score, while the best Pass@3 is 56.78%. Deterministic diagnostics, read from each task's best of 3 attempts and macro-averaged across the 12 models, show higher base-amount agreement (97.8%) than deciding-account accuracy (56.3%). Together with the failure analysis, these results identify account selection and complete-entry composition as the main remaining challenges on CAB.

  • 3 authors
·
Sep 12

Multi-RADS Synthetic Radiology Report Dataset and Head-to-Head Benchmarking of 41 Open-Weight and Proprietary Language Models

Background: Reporting and Data Systems (RADS) standardize radiology risk communication but automated RADS assignment from narrative reports is challenging because of guideline complexity, output-format constraints, and limited benchmarking across RADS frameworks and model sizes. Purpose: To create RXL-RADSet, a radiologist-verified synthetic multi-RADS benchmark, and compare validity and accuracy of open-weight small language models (SLMs) with a proprietary model for RADS assignment. Materials and Methods: RXL-RADSet contains 1,600 synthetic radiology reports across 10 RADS (BI-RADS, CAD-RADS, GB-RADS, LI-RADS, Lung-RADS, NI-RADS, O-RADS, PI-RADS, TI-RADS, VI-RADS) and multiple modalities. Reports were generated by LLMs using scenario plans and simulated radiologist styles and underwent two-stage radiologist verification. We evaluated 41 quantized SLMs (12 families, 0.135-32B parameters) and GPT-5.2 under a fixed guided prompt. Primary endpoints were validity and accuracy; a secondary analysis compared guided versus zero-shot prompting. Results: Under guided prompting GPT-5.2 achieved 99.8% validity and 81.1% accuracy (1,600 predictions). Pooled SLMs (65,600 predictions) achieved 96.8% validity and 61.1% accuracy; top SLMs in the 20-32B range reached ~99% validity and mid-to-high 70% accuracy. Performance scaled with model size (inflection between <1B and >=10B) and declined with RADS complexity primarily due to classification difficulty rather than invalid outputs. Guided prompting improved validity (99.2% vs 96.7%) and accuracy (78.5% vs 69.6%) compared with zero-shot. Conclusion: RXL-RADSet provides a radiologist-verified multi-RADS benchmark; large SLMs (20-32B) can approach proprietary-model performance under guided prompting, but gaps remain for higher-complexity schemes.

  • 25 authors
·
Jan 6

Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing

Practical video editing is not only pixel generation: an editor must turn a brief, a clip pool, music metadata, and hard constraints into an executable timeline. We study this decision layer as executable video-editing planning and introduce RefineCut, which, unlike workflow systems that wrap a prompted frontier model, trains a compact open-weight planner for it. The planner edits a typed timeline through structured patches covering clip selection, trimming, ordering, transitions, and duration and music alignment; a deterministic verifier applies each patch and checks it against an explicit constraint ledger. Because editing has no single ground-truth repair, we do not imitate teachers directly: RefineCut replays every multi-teacher branch through the verifier and keeps verifier-best repairs as supervision. A second stage, RefineCut-Evo, lets the student score its own repairs with the verifier and a task rubric and trains on high-margin preference pairs, so the final 8B planner runs in a closed verifier loop with no teacher calls at inference. On RefineCut-Bench (3{,}578 tasks, 7{,}971 captioned clips, 499 music tracks, explicit ledgers), verifier-replayed distillation lifts the planner from 0.620 to 0.858 on the protocol-specific Video-Editing Score and RefineCut-Evo reaches 0.924; the gain transfers to Llama-3.1-8B and GLM-4-9B, and in the same closed loop the 8B planner matches or exceeds its frontier teachers. Code and RefineCut-Bench are publicly released; see the Data Availability statement.

  • 8 authors
·
Aug 25

KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks, and do not directly measure LLMs' ability to generate executable commands for real-world cybersecurity tools. This gap is critical because cybersecurity operations rely on strict command-line interfaces (CLIs), where minor syntax errors, incorrect flag--value bindings, or argument misordering can invalidate execution. We introduce KaliBench, a fine-grained benchmark and dataset for natural-language--to--CLI translation on Kali Linux, comprising 8,504 query--command pairs spanning 1,642 tools across 23 capability dimensions and 5 security phases. KaliBench is constructed via a manuscript-grounded pipeline with deterministic canonicalization and alias-aware evaluation, enabling precise and reproducible assessment of tool selection and argument construction. To ensure both semantic correctness and practical executability, we develop a multi-stage verification pipeline that combines LLM-based validation, sandboxed terminal execution, and human-in-the-loop refinement. Building on these fine-grained, deterministic signals, KaliBench further enables runtime-free verifiable rewards for training. Across three evaluation modes and 24 configurations of general-purpose and security-focused open-weight models, no open-weight model exceeds 42% exact-command accuracy in the unrestricted setting, highlighting the difficulty of accurate CLI-based cybersecurity tool use without explicit tool hints. We further show that supervised fine-tuning and reinforcement learning with verifiable rewards derived from KaliBench significantly improve an 8B model and achieve performance comparable to a 685B MoE model.

Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety

Large language models (LLMs) trained on internet-scale corpora can exhibit systematic biases that increase the probability of unwanted behavior. In this study, we examined potential biases towards synthetic vs. biological technological solutions across four domains (materials, energy, manufacturing, and algorithms). A sample of 5 frontier and 5 open-weight models were measured using 50 curated Bioalignment prompts with a Kelly criterion-inspired evaluation framework. According to this metric, most models were not bioaligned in that they exhibit biases in favor of synthetic (non-biological) solutions. We next examined if fine-tuning could increase the preferences of two open-weight models, Llama 3.2-3B-Instruct and Qwen2.5-3B-Instruct, for biological-based approaches. A curated corpus of ~22M tokens from 6,636 PMC articles emphasizing biological problem-solving was used first to fine-tune Llama 3B with a mixed corpus of continued training and instruction-formatted. This was then extended to Qwen 3B using instruction-formatted only. We found that QLoRA fine-tuning significantly increased the scoring of biological solutions for both models without degrading general capabilities (Holm-Bonferroni-corrected p < 0.001 and p < 0.01, respectively). This suggests that even a small amount of fine-tuning can change how models weigh the relative value of biological and bioinspired vs. synthetic approaches. Although this work focused on small open-weight LLMs, it may be extensible to much larger models and could be used to develop models that favor bio-based approaches. We release the benchmark, corpus, code, and adapter weights.

  • 2 authors
·
Mar 9

When Agents Fail to Act: A Diagnostic Framework for Tool Invocation Reliability in Multi-Agent LLM Systems

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic framework that leverages big data analytics to evaluate procedural reliability in intelligent agent systems, addressing critical needs for SME-centric deployment in privacy-sensitive environments. Our approach features a 12-category error taxonomy capturing failure modes across tool initialization, parameter handling, execution, and result interpretation. Through systematic evaluation of 1,980 deterministic test instances spanning both open-weight models (Qwen2.5 series, Functionary) and proprietary alternatives (GPT-4, Claude 3.5/3.7) across diverse edge hardware configurations, we identify actionable reliability thresholds for production deployment. Our analysis reveals that procedural reliability, particularly tool initialization failures, constitutes the primary bottleneck for smaller models, while qwen2.5:32b achieves flawless performance matching GPT-4.1. The framework demonstrates that mid-sized models (qwen2.5:14b) offer practical accuracy-efficiency trade-offs on commodity hardware (96.6\% success rate, 7.3 s latency), enabling cost-effective intelligent agent deployment for resource-constrained organizations. This work establishes foundational infrastructure for systematic reliability evaluation of tool-augmented multi-agent AI systems.

  • 3 authors
·
Jan 21

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Today's most advanced multimodal models remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good performance, effectively distilling these closed models into open ones. As a result, the community is still missing foundational knowledge about how to build performant VLMs from scratch. We present Molmo, a new family of VLMs that are state-of-the-art in their class of openness. Our key innovation is a novel, highly detailed image caption dataset collected entirely from human annotators using speech-based descriptions. To enable a wide array of user interactions, we also introduce a diverse dataset mixture for fine-tuning that includes in-the-wild Q&A and innovative 2D pointing data. The success of our approach relies on careful choices for the model architecture details, a well-tuned training pipeline, and, most critically, the quality of our newly collected datasets, all of which will be released. The best-in-class 72B model within the Molmo family not only outperforms others in the class of open weight and data models but also compares favorably against proprietary systems like GPT-4o, Claude 3.5, and Gemini 1.5 on both academic benchmarks and human evaluation. We will be releasing all of our model weights, captioning and fine-tuning data, and source code in the near future. Select model weights, inference code, and demo are available at https://molmo.allenai.org.

  • 51 authors
·
Sep 25, 2024 4

Joules-to-GDP: How Much Economic Value Do AI Systems Produce per Unit of Energy?

An AI system can produce more economically valuable work while delivering less value for the energy it consumes. We therefore ask: How much economic value does an AI system create per unit of energy consumed? We formalize economic value in two ways: (1) net dollar value, the output's dollar value minus AI-system execution cost, and (2) time saving, the expert's completion time minus the AI system's completion time. Dividing each by measured end-to-end energy yields Net Value per Joule (NVJ) and Time Saving per Joule (TSJ), reported in USD/MJ and hours/MJ. We study 220 public GDPval tasks across 44 occupations, serving five open-weight models locally and evaluating four accelerator types. First, the occupation groups where AI systems succeed most often, deliver the greatest dollar value, or save the most time do not necessarily provide the greatest economic return per joule. For example, among the tested tasks, engineering work delivers about 10% more net dollar value per task than software development. Yet software development delivers about 27% more net value per joule. Second, GLM 5.2 delivers the highest average net dollar value, at $72.27 per task using 0.430 MJ, equivalent in energy to about four hours of active laptop use. By contrast, Gemma 4 31B delivers 56% of that net dollar value using just 23% of the energy, achieving approximately 2.5 times the NVJ and 2.8 times the TSJ. Third, across four single-accelerator deployments, Qwen3.6-27B's NVJ varies by a factor of 4.32 and TSJ by 9.27, with B200 leading both. Additionally, one and eight H100s deliver similar net dollar value, but eight reduce completion time by 22% at 3.24 times the energy. Our framework makes output value and expert time saving under an energy budget explicit objectives for improving models, accelerators, and software, while offering a new basis for assessing AI's potential economic effect on occupational work.

  • 8 authors
·
Oct 22

The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size

Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law R(N) = N_eff/N = 1/(1+c(N-1)N^{-β}) where the regime exponent β classifies any configuration into one of three asymptotic regimes -- hard-ceiling at 1/c (β= 0), sublinear at N^β/c (0 < β< 1), or linear (βge 1), and a mean-field theorem predicts that peer count k and rounds τ during agent debate enter the dynamics only through their product kτ. The law applies at two levels: answer diversity and correctness redundancy. Across 44 (model times task times condition) cells spanning peer debate, self-correction, random-noise placebo, self-consistency, three open-weight families (Qwen, Llama, Ministral) at scales from 7B to 32B with a frontier API check (Gemini), thinking models, heterogeneous teams, and sparse communication, the functional form fits every condition at R^2 > 0.99; only (c, β) shifts. On free-form math, dense peer influence collapses the answer-level regime from sublinear into hard-ceiling; correctness-level fits remain hard-ceiling throughout. Three findings have practical implications. (i)~Thirty dense debating agents produce no more answer diversity than one on MMLU-Hard. (ii)~A noise placebo tracks self-correction on free-form math and at 4times scale, so within homogeneous teams the gain commonly attributed to ``debate'' comes from re-evaluation, not peer content. (iii)~A single N le 5 pilot predicts the N=30 structural ceiling, and within the configurations tested only architectural diversity (heterogeneous teams) lowers c and escapes the hard-ceiling regime, communication-mode interventions do not.

  • 2 authors
·
May 30 1

Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems

Despite initial successes and a variety of architectures, retrieval-augmented generation (RAG) systems still struggle to reliably retrieve and connect the multi-step evidence required for complicated reasoning tasks. Most of the standard RAG frameworks regard all retrieved information as equally reliable, overlooking the varying credibility and interconnected nature of large textual corpora. GraphRAG approaches offer potential improvement to RAG systems by integrating knowledge graphs, which structure information into nodes and edges, capture entity relationships, and enable multi-step logical traversal. However, GraphRAG is not always an ideal solution as it depends on high-quality graph representations of the corpus, which requires either pre-existing knowledge graphs that are expensive to build and update, or automated graph construction pipelines that are often unreliable. Moreover, systems following this paradigm typically use large language models to guide graph traversal and evidence retrieval, leading to challenges similar to those encountered with standard RAG. In this paper, we propose a novel RAG framework that employs the spreading activation algorithm to retrieve information from a corpus of documents interconnected by automatically constructed knowledge graphs, thereby enhancing the performance of large language models on complex tasks such as multi-hop question answering. Experiments show that our method achieves better or comparable performance to iterative RAG methodologies, while also being easily integrable as a plug-and-play module with a wide range of RAG-based approaches. Combining our method with chain-of-thought iterative retrieval yields up to a 39\% absolute gain in answer correctness compared to naive RAG, achieving these results with small open-weight language models and highlighting its effectiveness in resource-constrained settings.

  • 3 authors
·
Dec 17, 2025

H2LooP Spark Preview: Continual Pretraining of Large Language Models for Low-Level Embedded Systems Code

Large language models (LLMs) demonstrate strong code generation abilities in general-purpose programming languages but remain limited in specialized domains such as low-level embedded systems programming. This domain involves hardware register manipulation, vendor-specific SDKs, real-time operating system APIs, and hardware abstraction layers that are underrepresented in standard pretraining corpora. We introduce H2LooP Spark Preview, a continual pretraining (CPT) pipeline that adapts the OLMo-3-7B-a fully open language model to the embedded systems domain using BF16 LoRA with rank-stabilized scaling on 8 NVIDIA H100 GPUs. Our training corpus is constructed from repository-datasheet pairs covering 100B tokens of raw embedded systems data across 117 manufacturers, processed using the hierarchical datasheet-to-code mapping approach proposed in SpecMap (Nipane et al., 2026). The resulting curated dataset split contains 23.5B tokens across 13 embedded domains. Continual pretraining with high-rank LoRA (r=512) yields substantial gains, reducing in-domain perplexity by 70.4% and held-out repository perplexity by 66.1%. On generative code completion benchmarks spanning 13 embedded domains, our 7B model outperforms Claude Opus 4.6 and Qwen3-Coder-30B on 8 categories in token accuracy, showing that targeted continual pretraining enables smaller open-weight models to rival frontier systems on specialized technical tasks. We release the production training checkpoint on Huggingface as an open-source artifact.

  • 5 authors
·
Mar 12

SERA: Soft-Verified Efficient Repository Agents

Open-weight coding agents should hold a fundamental advantage over closed-source systems: they can be specialized to private codebases, encoding repository-specific information directly in their weights. Yet the cost and complexity of training has kept this advantage theoretical. We show it is now practical. We present Soft-Verified Efficient Repository Agents (SERA), an efficient method for training coding agents that enables the rapid and cheap creation of agents specialized to private codebases. Using only supervised finetuning (SFT), SERA achieves state-of-the-art results among fully open-source (open data, method, code) models while matching the performance of frontier open-weight models like Devstral-Small-2. Creating SERA models is 26x cheaper than reinforcement learning and 57x cheaper than previous synthetic data methods to reach equivalent performance. Our method, Soft Verified Generation (SVG), generates thousands of trajectories from a single code repository. Combined with cost-efficiency, this enables specialization to private codebases. Beyond repository specialization, we apply SVG to a larger corpus of codebases, generating over 200,000 synthetic trajectories. We use this dataset to provide detailed analysis of scaling laws, ablations, and confounding factors for training coding agents. Overall, we believe our work will greatly accelerate research on open coding agents and showcase the advantage of open-source models that can specialize to private codebases. We release SERA as the first model in Ai2's Open Coding Agents series, along with all our code, data, and Claude Code integration to support the research community.

ai21labs AI21
·
Jan 28 2

FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis

We introduce FindStatBench, an execution benchmark for evaluating large language models on combinatorial code synthesis. Built from FindStat, it contains 2,329 tasks across 24 collections and 5.52M hidden instances, covering statistic synthesis, which maps objects to integers, and map synthesis, which maps objects to objects. Each task gives a mathematical description and at most five public input-output examples; a model must emit one Python solve function with no retrieval, tool use, execution feedback, voting, or reranking. Submissions are scored by exact sandboxed execution on held-out combinatorial objects. We evaluate eleven systems: four closed-source production models and seven open-weight models served through one inference provider. FindStatBench reveals three main patterns. First, the strongest open- and closed-source systems converge within 1 pp instance accuracy, and both an oracle over all systems and five-way sampling from one mid-tier model yield only limited task-accuracy gains. Second, examples can hurt: several classical bijections are solved perfectly with zero examples but fail under five-example prompts. Third, some failures reflect output-budget mechanics, as reasoning can exhaust the visible response before code is emitted. Overall, statistic synthesis is much easier than map synthesis, some collections remain near-zero, long prompts cause a sharp accuracy cliff, and exact symbolic rule induction remains brittle.

  • 1 authors
·
May 15

A Different Approach to AI Safety: Proceedings from the Columbia Convening on Openness in Artificial Intelligence and AI Safety

The rapid rise of open-weight and open-source foundation models is intensifying the obligation and reshaping the opportunity to make AI systems safe. This paper reports outcomes from the Columbia Convening on AI Openness and Safety (San Francisco, 19 Nov 2024) and its six-week preparatory programme involving more than forty-five researchers, engineers, and policy leaders from academia, industry, civil society, and government. Using a participatory, solutions-oriented process, the working groups produced (i) a research agenda at the intersection of safety and open source AI; (ii) a mapping of existing and needed technical interventions and open source tools to safely and responsibly deploy open foundation models across the AI development workflow; and (iii) a mapping of the content safety filter ecosystem with a proposed roadmap for future research and development. We find that openness -- understood as transparent weights, interoperable tooling, and public governance -- can enhance safety by enabling independent scrutiny, decentralized mitigation, and culturally plural oversight. However, significant gaps persist: scarce multimodal and multilingual benchmarks, limited defenses against prompt-injection and compositional attacks in agentic systems, and insufficient participatory mechanisms for communities most affected by AI harms. The paper concludes with a roadmap of five priority research directions, emphasizing participatory inputs, future-proof content filters, ecosystem-wide safety infrastructure, rigorous agentic safeguards, and expanded harm taxonomies. These recommendations informed the February 2025 French AI Action Summit and lay groundwork for an open, plural, and accountable AI safety discipline.

  • 20 authors
·
Jun 27, 2025

AHELM: A Holistic Evaluation of Audio-Language Models

Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters. To address these shortfalls, we introduce AHELM, a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE, which evaluates the ALMs on avoiding stereotypes, and CoRe-Bench, which measures reasoning over conversational audio through inferential multi-turn question answering -- to holistically measure the performance of ALMs across 10 aspects we have identified as important to the development and usage of ALMs: audio perception, knowledge, reasoning, emotion detection, bias, fairness, multilinguality, robustness, toxicity, and safety. We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models. We test 14 open-weight and closed-API ALMs from 3 developers and 3 additional simple baseline systems each consisting of an automatic speech recognizer and a language model. Our results show that while Gemini 2.5 Pro ranks top in 5 out of 10 aspects, it exhibits group unfairness (p=0.01) on ASR tasks whereas most of the other models do not. We also find that the baseline systems perform reasonably well on AHELM, with one ranking 5th overall despite having only speech-to-text capabilities. For transparency, all raw prompts, model generations, and outputs are available on our website at https://crfm.stanford.edu/helm/audio/v1.0.0. AHELM is intended to be a living benchmark and new datasets and models will be added over time.

  • 9 authors
·
Aug 29, 2025 5

Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark

Vision-language models (VLMs) are increasingly deployed where answers must follow from what is in the image, yet they often answer from textual priors, the question's phrasing together with memorized world knowledge, rather than from the image itself, which inflates benchmark scores and yields confident but ungrounded answers. Existing benchmarks rarely isolate this behavior, since each image is usually paired with a single fixed question. To measure the reliance, we build a 540-image benchmark across six reasoning categories and generate four question variants over the same images, so that phrasing rather than image content is the controlled variable. The hardest variant is written directly from the image to minimize text leakage. We benchmark eleven VLMs spanning small open-weight models to large closed-source systems: every model degrades on the hardest variant, and open models fall furthest. Our central diagnostic is a no-image ablation, which collapses the open-weight models to their text-only floor (1 to 9 percent). Three further analyses, LLM-rated difficulty, low base-to-final textual similarity, and human re-annotation, corroborate genuine image-dependence. In-context exemplars that match how a variant was built recover the most accuracy, and GRPO post-training of a small VLM yields consistent gains across all four variants that transfer to a held-out out-of-distribution set. Textual-prior reliance is measurable and partly trainable away.

  • 4 authors
·
Jun 8

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

As agentic systems tackle increasingly complex multi-step tasks, evaluating their trajectories presents a major bottleneck - human annotation of a single trajectory on popular agentic benchmarks can take hours, making it difficult to scale evaluations for measuring performance or curating training data. This has driven widespread reliance on automated approaches such as LLM-as-a-judge (LLMJ) to critique agents at the process and outcome-levels at scale, however, the soundness of LLMJ critiques often goes unmeasured. Here, we introduce Counsel, the first public dataset of meta-evaluations for agentic tasks. Counsel consists of process-level critiques from open-weight LLMJs on two agent benchmarks: tau-bench (customer support agents) and DA-Code (coding agents), and human meta-evaluations of these critiques. Human annotators label critiques on each flagged error as "spot on", "correct location but poor reasoning", or "should not have flagged", achieving reliable inter-annotator agreement (Krippendorff's alpha of 0.78). The resulting dataset stratifies LLMJ critiques by human alignment across both error location within a trajectory and reasoning quality, serving as valuable data to calibrate, improve, or train LLMJs for agents. Comparing open-weight judges, we find that more capable judge models and more reasoning effort both enabled improved human agreement, with the strongest judge reaching ~88% agreement on location and ~65% on reasoning. Counsel is generated using open-weight models and is permissively licensed for broad community use, which we hope will enable rigorous study and improved alignment of LLM-based evaluators for agentic systems.

AtlaAI Atla
·
Jun 18 1

AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model

General-purpose large language models, despite their broad capabilities, often struggle with specialized domain knowledge, a limitation particularly pronounced in more accessible, lower-parameter versions. This gap hinders their deployment as effective agents in demanding fields such as astronomy. Building on our prior work with AstroSage-8B, this study introduces AstroSage-70B, a significantly larger and more advanced domain-specialized natural-language AI assistant. It is designed for research and education across astronomy, astrophysics, space science, astroparticle physics, cosmology, and astronomical instrumentation. Developed from the Llama-3.1-70B foundation, AstroSage-70B underwent extensive continued pre-training on a vast corpus of astronomical literature, followed by supervised fine-tuning and model merging. Beyond its 70-billion parameter scale, this model incorporates refined datasets, judiciously chosen learning hyperparameters, and improved training procedures, achieving state-of-the-art performance on complex astronomical tasks. Notably, we integrated reasoning chains into the SFT dataset, enabling AstroSage-70B to either answer the user query immediately, or first emit a human-readable thought process. Evaluated on the AstroMLab-1 benchmark -- comprising 4,425 questions from literature withheld during training -- AstroSage-70B achieves state-of-the-art performance. It surpasses all other tested open-weight and proprietary models, including leading systems like o3, Gemini-2.5-Pro, Claude-3.7-Sonnet, Deepseek-R1, and Qwen-3-235B, even those with API costs two orders of magnitude higher. This work demonstrates that domain specialization, when applied to large-scale models, can enable them to outperform generalist counterparts in specialized knowledge areas like astronomy, thereby advancing the frontier of AI capabilities in the field.

  • 10 authors
·
May 23, 2025

WebChallenger: A Reliable and Efficient Generalist Web Agent

Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference cost is prohibitive for the repetitive tasks where such agents would be most useful. We argue this gap stems not from insufficient model capability but from agent architectures that fail to replicate three human cognitive advantages: selective attention to relevant page regions, persistent memory of website structure, and procedural fluency with common interaction patterns. We introduce WebChallenger, a web agent framework that addresses each gap through architecture design rather than model scale, built around PageMem: a structured page representation deterministically constructed from the DOM that exposes each page as a hierarchy of semantic sections with short summaries. On this shared substrate we build three mechanisms that mirror the three cognitive advantages: a divide-and-conquer observation pipeline that lets the agent skim section summaries and extract details only from task-relevant regions; a lightweight exploration and memory system that traverses each website once to build a reusable map of pages and element behaviors; and compound action workflows that collapse common multi-step interactions into single agent actions, handling partial state changes automatically. Because all three operate over PageMem, the framework generalizes across websites without site-specific adapters. Using off-the-shelf open-weight models without fine-tuning, our system achieves 56.3% on WebArena, 48.7% on VisualWebArena, 51.0% on Online-Mind2Web, and 70.9% on WorkArena, approaching frontier proprietary systems at a fraction of the cost. Our code is released at https://github.com/jayoohwang1/webchallenger

  • 3 authors
·
Jun 8 4

MolmoAct2: Action Reasoning Models for Real-world Deployment

Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. Frontier models are closed, open-weight alternatives are tied to expensive hardware, reasoning-augmented policies pay prohibitive latency for their grounding, and fine-tuned success rates remain below the threshold for dependable use. We present MolmoAct2, a fully open action reasoning model built for practical deployment, advancing its predecessor along five axes. We introduce MolmoER, a VLM backbone specialized for spatial and embodied reasoning, trained on a 3.3M-sample corpus with a specialize-then-rehearse recipe. We release three new datasets spanning low-to-medium cost platforms, including MolmoAct2-BimanualYAM, 720 hours of teleoperated bimanual trajectories that constitute the largest open bimanual dataset to date, together with quality-filtered Franka (DROID) and SO100/101 subsets. We provide OpenFAST, an open-weight, open-data action tokenizer trained on millions of trajectories across five embodiments. We redesign the architecture to graft a flow-matching continuous-action expert onto a discrete-token VLM via per-layer KV-cache conditioning. Finally, we propose MolmoThink, an adaptive-depth reasoning variant that re-predicts depth tokens only for scene regions that change between timesteps, retaining geometric grounding at a fraction of prior latency. In the most extensive empirical study of any open VLA to date, spanning 7 simulation and real-world benchmarks, MolmoAct2 outperforms strong baselines including Pi-05, while MolmoER surpasses GPT-5 and Gemini Robotics ER-1.5 across 13 embodied-reasoning benchmarks. We release model weights, training code, and complete training data. Project page: https://allenai.org/blog/molmoact2

allenai Ai2
·
May 3 6

MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents

Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and collaborative work, are inherently multi-speaker. Supporting these settings introduces challenges that are largely absent from one-on-one interaction. We introduce the Multi-Speaker Interaction Benchmark (MSI-Bench) for evaluating multi-speaker voice interaction. Each test case is a short multi-party multi-turn audio scene with participant context, expected tool calls, and atomic rubrics. The benchmark targets three capability families: multi-speaker memory, multi-speaker instruction following, and multi-speaker reasoning. It comprises 1,152 test cases, evenly split between Mandarin Chinese and English (576 each). The strongest configuration on each split passes all rubrics on only 66.8% of English and 54.5% of Mandarin cases, and the strongest open-weight configuration on 34.0% and 19.3%. Failure analysis separates perception from reasoning: open-weight models are bottlenecked by the multi-speaker audio front-end, while frontier systems still fail speaker-scoped decision making on clean transcripts---and models across the board often respond when no one has addressed them. These results identify speaker-grounded perception, speaker-scoped decision making, and conversational restraint as concrete targets for future voice agents.

  • 6 authors
·
Sep 20

Generalizing Manipulation Skills with a Local Coding Agent

Today, progress in open-weight language models enables systems capable of writing, executing and debugging code while still running on a single workstation. Most language-driven robots give the model a fixed action interface or a trained policy. Generalizing to a new task therefore means more engineering effort or more data collection, both time-consuming. We investigate whether a local open-weight vision-language model can control a robot and one-shot generalize to new variations of a task without new human programming or training. We let a local open-weight VLM, Qwen3.8-27B, drive a UR3e robotic arm from a coding-agent harness. It writes and runs its own code above a service that implements kinematics, safety limits and classic computer vision techniques. We investigate if this system is capable of generalizing to unseen tasks. Specifically, we test it on nine tasks built from children's toys designed to probe generalization capability across various object characteristics: color, size, shape, and task variation of those. With five trials for each task, we observe generalization in 30 out of 45 trials with durations ranging from 3.4 to 67.5 minutes depending on task complexity. We further test if there is a speedup when an agent is asked to redo the task after successful completion. This resulted in a 50% reduction in duration, indicating that there is self-improvement over time. Finally, we expose the limitations of a local coding agent. We believe that solving those limitations combined with further investigation of self-improvement over time points at a direct path toward real-world deployment of a local coding agent.

  • 4 authors
·
Sep 21

Don&#39;t Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons

Intelligent agents should learn from their mistakes so that experience leads to continuous improvement. Yet today's agents recover from a mistake only temporarily: in-context reflections are easily forgotten across sessions and compete for limited context, while full-parameter fine-tuning is expensive and can interfere with existing capabilities. We introduce Self-Direction, a mechanism for agents to learn from mistakes that combines the benefits of temporary in-context retries and policy updates. When an agent fails a task, it reflects on its own trajectory in order to extract a lesson and immediately distills it into a lightweight low-rank adapter. By keeping the original weights frozen, Self-Direction prevents adapter training from overwriting base-model parameters while training additional parameters equivalent to ~0.02% of the base model's parameter count for each adapter. The agent then saves these adapters in a persistent library of lessons, automatically routing them to solve related problems later. Experiments with agents based on open-weight models from the Qwen family across open-ended research (GAIA), tool-use workflows (Claw-Eval), and terminal tasks (Terminal-Bench 2.1) show that our method improves overall success rates by 8.9 to 17.0 percentage points and performs competitively with frontier systems. We find that Self-Direction reduces repeated mistakes across future encounters of a task, nearly doubling the reliability of an agent's corrections. Learned lessons also transfer: a handful of adapters generalize to dozens of new tasks without additional training. Ultimately, this self-directed repair transforms everyday mistakes into lasting lessons.

  • 7 authors
·
Oct 21

How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning

Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning. On-policy distillation narrows such gaps by supervising a student on its own rollouts, but traditional OPD requires a strong external teacher, and on-policy self-distillation (OPSD) conditions on a full reference solution. We ask how much of that signal is necessary. We present Fin-SD, a localized hindsight self-distillation recipe for multi-step reasoning. Given a problem the student fails, the student itself identifies the first incorrect reasoning step and writes a short critique of that step. We truncate the student's trajectory immediately before the error (aiming to obtain a correct prefix), condition a frozen copy of the student on the same prefix plus the hint, and distill that hint-conditioned teacher into the student over a short rollout under reverse KL. No external model contributes a gradient. We apply Fin-SD to GPT-OSS-20B on a custom multi-step financial reasoning benchmark that requires deriving formula inputs from realistic scenarios via accounting conventions. We find: (i) replacing the critique with a generic-feedback control matches Fin-SD's entire 3.03 pp accuracy gain over the base model on the FinanceReasoning Hard subset, suggesting the gain comes from where supervision is applied, not hint content; (ii) the model writing the hint does not need to be stronger than the model receiving it: hints from same-family GPT-OSS-120B, at roughly 6x the parameters, yield no materially greater benefits than self-written hints; and (iii) Fin-SD matches on-policy self-distillation from full reference solutions on accuracy while generating 9.5% fewer tokens. With Fin-SD, general reasoning on MMLU-Pro and a fourteen-metric compliance audit on FinTrust show no material regression.

ctgt-inc CTGT, Inc.
·
Oct 25 2

AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness

Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verification. Despite rapid progress, research-level proofs often depend on concepts missing from leading proof assistant libraries (e.g., Lean's Mathlib), and successful compilation does not guarantee that a translation preserves the theorem's meaning or the proof's reasoning. Furthermore, aligned NL-FL training data are scarce, and leading agents often rely on costly frontier models and manually engineered harnesses. To address the above issues, we present AIProver, an agentic framework for autonomous proof auto-formalization and proof synthesis (AFPS) that jointly post-trains a 119B open-weight language model and evolves its agentic, tool-calling harness with HarnessEvolve. Verifiers assess type correctness, proof completeness, and semantic correctness, returning rewards and diagnostic certificates that drive model fine-tuning and alternating reinforcement learning via symbolic feedback and HarnessEvolve, a certificate-driven evolutionary search over the whole harness control flow that re-tailors the harness to the updated model. For research-level training and evaluation, we introduce LoCoBench, 58.9k instances from Mathlib, CSLib, Mizar Math Library, and a bounded-arithmetic textbook, with a 771-instance validation split whose theorem-proof pairs have no public Lean formalization. Against 39 frameworks spanning AFPS agents, frontier LLMs, and coding agents, AIProver lifts pass@4 semantic correctness over its Leanstral-1.5 base from 15.7% to 36.7% and outperforms every other open-weight system and Aristotle. As a Claude Code and Codex skill, it lifts their semantic correctness from 41.9% and 34.1% to 79.8% and 62.4%, respectively. Further, it is also 24% cheaper than Numina-Lean-Agent, pushing the accuracy-cost frontier of research-level AFPS.

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Training capable cyber agents is often treated primarily as a problem of model scale, yet open-weight post-training is constrained more directly by the cost of executable environments, reliable multi-turn supervision, and access to strong teachers. We present a data-centric framework that addresses these bottlenecks through five complementary systems: Choulea analyzes hidden reasoning signatures, SkyReal reduces teacher-sampling cost, Hongzwang bypasses API restrictions on teacher execution, PSBreakup restores capabilities weakened by model merging, and Kreator converts expert interventions into trainable reasoning. Our data engine constructs resettable coding, vulnerability, CTF, kernel-history, full-exploit, firmware, and device-backed environments. Candidate trajectories are retained only after execution verification and evidence auditing, yielding 164,269 trajectories for long-context supervised fine-tuning. The three checkpoints improve over their starting models by an average of 23.76% on the full CyberGym suite and 10.49% across the pooled CTF suites. As of September 1, 2026, Feyospace-s1 achieves a verified success rate of 63.24% and ranks 10th on the official CyberGym leaderboard, while all three checkpoints rank 1st among models at comparable parameter scales. To our knowledge, this is the first end-to-end demonstration that a seven-person independent team can train open-weight models with leading agentic cyber capability.

feyospace feyospace
·
Sep 7 3

DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29\%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.

  • 9 authors
·
May 13

MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents

We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful execution environment spanning 500+ tools across 16 application domains, supporting multi-image, multi-turn tasks where agents must ground progressively arriving visual inputs into executable tool calls while handling realistic conversational phenomena (goal revisions, error corrections, state mutations). An automated scenario generation pipeline produces diverse, visually grounded scenarios through information-flow-guided planning and multi-stage quality filtering, yielding 258 human-verified nominal scenarios and 50 variants targeting interactive UI applications. Evaluating 12 state-of-the-art models, from 4B open-weight to frontier proprietary systems, shows that current models still lack robust visual tool-calling capability: even the best model achieves below 50% success rate. Our failure analysis further reveals that visual precision, not only planning, is a primary bottleneck for capable models: 53% of failures stem from incorrect information extraction from images despite otherwise correct task workflows. A planning-to-precision crossover emerges with scale: smaller models fail at deciding what to do, while larger models fail at perceiving what they see, suggesting fundamentally different research directions for improving models at different capability levels. The framework and the benchmark are publicly available at https://github.com/apple/ml-mmtoolsandbox

  • 6 authors
·
Aug 20

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry query, and enrichment request consumes budget. We evaluate language-model security agents through this cost-success lens on offensive Cybench challenges and defensive Splunk BOTS v1 investigation challenges. Instead of reporting only best-case success, we compare models at fixed cost levels and decompose performance by inference spend and tool spend. Our results show distinct scalingregimes for red- and blue-team tasks. Offensive CTF performance improves with additional test-time compute, and scaled open-weight models can approach frontier proprietary systems while remaining cost-competitive. Defensive SOC investigation does not scale in the same way: success depends more heavily on disciplined tool use, telemetry navigation, and selective enrichment than on raw reasoning budget alone. We argue that security-agent benchmarks should measure economic efficiency and operational fit alongside task success. Cost-aware, SOC-native evaluations provide a clearer picture of which models are practically useful today and where defensive agents still need to improve. We present an interactive website with our results https://evals.frontier.security.

  • 3 authors
·
Jul 16 2

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content

Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak attempts, and unsafe responses without the cost profile of large guardrail models, and that can distinguish benign sensitive text from genuinely covert harmful content. In this paper, we introduce Opir, a family of encoder-based guardrail models built on the GLiClass architecture. Opir includes multi-task models for binary safe/unsafe classification, multi-label toxicity classification, jailbreak classification, and zero-shot unsafe prompt and response categorization. We also release edge variants with fewer than 100M parameters dedicated to binary safe/unsafe categorization. The models are trained on a three-level taxonomy containing 996 categories across 16 top-level labels, 126 mid-level labels, and 854 leaf labels. Opir's training data combines taxonomy-grounded unsafe prompts, adversarially mined hard negatives, benign safety-preserving examples, generated response examples, multilingual translations, and portions of the Aegis2 and WildGuard training subsets. We also open-sourced an evaluation harness that supports GLiClass and GLiNER2 backends as well as decoder-based models, and covers binary safety classification, multi-label categorization, toxicity, jailbreak detection, prompt safety, response safety, response refusal, and prompt subcategory views across public benchmark families. Across an expanded comparison spanning 12 safety-classification tasks and 17 category tasks against eight contemporary guardrail systems -- including both GLiNER2-based and generative guardrail models -- Opir variants are competitive on or ahead of the strongest open-weight baselines on the majority of benchmark datasets while operating with a substantially smaller deployment footprint.

  • 2 authors
·
May 27

HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery

Scientific discovery with language models requires finding the best valid solution within a finite computational budget. We study how feedback from this search can improve the procedure used to conduct it. We introduce HarnessTTT, a test-time learning framework that trains a harness proposer while keeping the executor frozen. The proposer generates executable harnesses comprising system prompts, reusable skills, tools, middleware, and execution controls. Each harness guides a budgeted discovery rollout, whose outcome provides feedback for updating the proposer. A discovery-oriented policy-gradient objective combines gap-normalized rewards, leave-one-out advantages (RLOO), and max-sharpening to favor high-performing proposals. Generated components are validated before execution, and the search retains the best valid solution and selected harnesses across rounds. Across fourteen discovery tasks in mathematics, systems, GPU kernels, heuristic programming, astrodynamics, and biology, HarnessTTT with a frozen 9B executor improves on OpenEvolve with the same executor on all eleven benchmark tasks (e.g., from 1.17 to 2.64 on circle packing), improves on the discovery-fine-tuned Finch-9B by up to 92%, holds the best open-weight sub-10B result on nine, and reaches 0.380919 on Erdős minimum overlap, better than the best human reference of 0.380927. Scaling the proposer and frozen executor to 27B improves on eleven of fourteen tasks, and transferring the learned harnesses to GPT-5.5 matches or exceeds the strongest reported system of any backbone on nine of fourteen tasks. Together, these results show that harness search can itself be learned at test time: a trained proposer lets a small frozen executor search effectively, and the harnesses it finds carry over to stronger executors.

  • 8 authors
·
Oct 11

Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF

This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline --- from tokenisation and vectorisation to fine tuning of large language models, retrieval augmented generation, reinforcement learning from human feedback, prompt engineering, model compression, and multimodal systems. Seventeen hands-on sessions combine concise theory with detailed implementation plans, formalised evaluation metrics, and transparent assessment criteria. The work is not a conventional textbook: it is designed as a reproducible research artefact where every session requires publishing code, models, and reports in public repositories. All experiments are conducted on a single evolving corpus, and the work advocates open weight models over commercial APIs, with special attention to the Hugging Face ecosystem. The material is enriched by original research on low resource languages, incorporating linguistic resources for Tajik and Tatar --- subword tokenisers, embeddings, lexical databases, and transliteration benchmarks --- demonstrating how modern NLP can be adapted to data scarce environments. The practicum also covers advanced topics including AI agents, multi-agent systems, LLMOps, and efficient inference, preparing students for both research and industrial deployment. Designed for senior undergraduates, graduate students, and practising developers seeking to implement, compare, and deploy methods from classical ML to state of the art multimodal and agent-based systems.

  • 1 authors
·
Aug 12

AutoMem: Automated Learning of Memory as a Cognitive Skill

Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill. We promote file-system operations to first-class memory actions alongside task actions, letting the model itself decide how to manage its memory. This memory skill improves along two axes: the structure that supports it (prompts, file schemas, action vocabulary), and the proficiency of the model exercising it. Both axes resist manual optimization: episodes in long-horizon tasks run for thousands of steps, and a single memory mistake can hide long before it surfaces, making human review of full trajectories impractical. We introduce AutoMem, a framework that automates both axes. In the first loop, a strong LLM reviews complete agent trajectories and iteratively revises the memory structure that shapes how the agent interacts with its memory files. In the second loop, the agent's own good memory decisions are identified from many episodes and used as training signal to sharpen the model's memory proficiency directly. Across three procedurally generated long-horizon games (Crafter, MiniHack, and NetHack), optimizing memory alone--without modifying the model's task-action behavior--improved the base agent's performance ~2x-4x, bringing a 32B open-weight model competitive with frontier systems such as Claude Opus 4.5 and Gemini 3.1 Pro Thinking. Our results show that memory management is an independently learnable skill, and a high-leverage objective yielding large gains on long-horizon tasks.

  • 5 authors
·
Jun 30 3

A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space

Open-set object detection (OSOD) is highly desirable for robotic manipulation in unstructured environments. However, existing OSOD methods often fail to meet the requirements of robotic applications due to their high computational burden and complex deployment. To address this issue, this paper proposes a light-weight framework called Decoupled OSOD (DOSOD), which is a practical and highly efficient solution to support real-time OSOD tasks in robotic systems. Specifically, DOSOD builds upon the YOLO-World pipeline by integrating a vision-language model (VLM) with a detector. A Multilayer Perceptron (MLP) adaptor is developed to transform text embeddings extracted by the VLM into a joint space, within which the detector learns the region representations of class-agnostic proposals. Cross-modality features are directly aligned in the joint space, avoiding the complex feature interactions and thereby improving computational efficiency. DOSOD operates like a traditional closed-set detector during the testing phase, effectively bridging the gap between closed-set and open-set detection. Compared to the baseline YOLO-World, the proposed DOSOD significantly enhances real-time performance while maintaining comparable accuracy. The slight DOSOD-S model achieves a Fixed AP of 26.7%, compared to 26.2% for YOLO-World-v1-S and 22.7% for YOLO-World-v2-S, using similar backbones on the LVIS minival dataset. Meanwhile, the FPS of DOSOD-S is 57.1% higher than YOLO-World-v1-S and 29.6% higher than YOLO-World-v2-S. Meanwhile, we demonstrate that the DOSOD model facilitates the deployment of edge devices. The codes and models are publicly available at https://github.com/D-Robotics-AI-Lab/DOSOD.

  • 7 authors
·
Dec 19, 2024

Bongard: Training Machine Intuition

Human intelligence relies heavily on learned intuition: recognising patterns and judging situations without explicitly unfolding every intermediate step. We introduce Bongard, an open-weight System One model that treats machine intuition as an independent capability to design and train. A T5Gemma 2 4B-4B encoder-decoder separates reading the evidence from making judgments. The encoder reads the state bidirectionally together with the question instructions, and separate decoder branches share this encoding, so many judgments about the same situation require only one reading of the state. A trained head returns probabilities over the supplied candidates without generating text. Training proceeds in three stages, from supervised judgments to semantic relationships to action outcomes, and each stage updates all 7.09 billion trainable parameters on one Blackwell GPU. Joint-embedding post-training raises accuracy on held-out rephrasings from 75.7% to 85.9%. A sandbox stage then learns outcome distributions from action rollouts and exact oracles, raising accuracy on a frozen sandbox panel from 50.6% to 64.8%. On DecisionBench, the final model reaches 78.05% accuracy over 23,900 decisions and ranks fourth of 61 systems in the public comparison. On one RTX PRO 6000, its median latency is 36 ms for short requests, and 32 questions about one state take 221 ms. Bongard demonstrates that machine intuition can be systematically trained via representation learning and outcome feedback, providing an open, efficient alternative for high-throughput decision workloads.

  • 3 authors
·
Sep 29

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by jailbreaking the model. Yet, pretrained LLMs already encode substantial harmful knowledge across many domains, which raises an important question: can an adversary jailbreak safeguarded models, to achieve harmful usage without fine-tuning at all? In this paper, we show that open-weight safeguards are susceptible to simpler strategies that, despite being well known, have not been systematically evaluated against these safeguards. Specifically, we evaluate two low-cost attacks--abliteration and prefilling--that do not rely on gradient-based optimization. Across three harmfulness evaluation benchmarks (BeaverTails, HarmBench, and AdvBench), these attacks increase attack success rates against safeguarded open-weight models from below 10\% to a range of 16%-96%. To mitigate this vulnerability, we introduce abliteration-resistant tuning (ART), which incorporates an abliteration-based objective into training. ART can be layered onto existing defenses and reduces the success rates of abliteration, prefilling, and their combination by 10%-20%. These findings indicate that the attack surface for open-weight models is broader than previously characterized, and that evaluations of safeguarding defenses should incorporate a more diverse set of attack strategies beyond adversarial fine-tuning.

  • 3 authors
·
Oct 5

Rethinking Pulmonary Embolism Segmentation: A Study of Current Approaches and Challenges with an Open Weight Model

Pulmonary Embolism (PE) is a life-threatening condition for which accurate and timely detection is critical to patient care. However, our systematic study of PE segmentation algorithms reveals concerning limitations in the current state of research. Challenges such as small and inconsistent datasets, a lack of reproducible baselines, and limited comparative evaluation across models are hindering progress in the field. In this study, we curated a densely annotated dataset comprising 490 CTPA scans, each from a unique patient (430 for training and 60 for testing). We evaluated nine widely used segmentation architectures, including both CNN- and ViT-based models, in 2D and 3D configurations, using mean Dice Similarity Coefficient (mDSC) and Average Symmetric Surface Distance (ASSD) as evaluation metrics. Furthermore, the highest-performing model was evaluated on a public dataset without fine-tuning and achieved reasonable generalization performance. Our results show that: (1) a 3D U-Net with ResNet encoding blocks remains a highly effective architecture for PE segmentation; (2) 3D models consistently outperform their 2D counterparts; (3) across all architectures, when trained and evaluated on the same datasets, model error patterns are highly consistent; and (4) distal emboli remain particularly challenging due to both task complexity and the scarcity of high-quality datasets, highlighting the need for datasets with more comprehensive and consistent distal PE coverage. To promote research reproducibility, the architecture and pretrained weights of our best-performing model are publicly available at https://github.com/mazurowski-lab/PulmonaryEmbolismSegmentation

  • 5 authors
·
Apr 28

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent misalignment, some models showed more resistance than others. Specifically the Qwen-2.5 family proved to be relatively resistant, while GPT-4o exhibited the strongest misalignment. In this paper we evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family and measure misalignment robustness over a range of model architectures and scales. We replicate the effect across nine modern open-weights models (Gemma 3 and Qwen 3 families, 1B-32B parameters). Models fine-tuned on insecure code generation show a 0.68% misalignment rate (compared to 0.07% for base models), matching the lower end of prior open-model results but dramatically lower than GPT-4o's 20%. We identify a critical format-dependent vulnerability: requiring JSON output doubles misalignment rates compared to natural language prompts (0.96% vs 0.42%). This suggests that structural constraints may bypass safety training by reducing the model's 'degrees of freedom' to refuse. These findings confirm emergent misalignment as a reproducible phenomenon in modern open-weights models, with rates substantially lower than observed in proprietary systems.

  • 1 authors
·
Nov 25, 2025

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks. However, there is no standard approach to evaluate tamper resistance. Varied data sets, metrics, and tampering configurations make it difficult to compare safety, utility, and robustness across different models and defenses. To this end, we introduce TamperBench, the first unified framework to systematically evaluate the tamper resistance of LLMs. TamperBench (i) curates a repository of state-of-the-art weight-space fine-tuning attacks and latent-space representation attacks; (ii) enables realistic adversarial evaluation through systematic hyperparameter sweeps per attack-model pair; and (iii) provides both safety and utility evaluations. TamperBench requires minimal additional code to specify any fine-tuning configuration, alignment-stage defense method, and metric suite while ensuring end-to-end reproducibility. We use TamperBench to evaluate 21 open-weight LLMs, including defense-augmented variants, across nine tampering threats using standardized safety and capability metrics with hyperparameter sweeps per model-attack pair. This yields novel insights, including effects of post-training on tamper resistance, that jailbreak-tuning is typically the most severe attack, and that Triplet emerges as a leading alignment-stage defense. Code is available at: https://github.com/criticalml-uw/TamperBench

  • 11 authors
·
Feb 5

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models

Large Language Models (LLMs) have achieved remarkable advancements, but their monolithic nature presents challenges in terms of scalability, cost, and customization. This paper introduces the Composition of Experts (CoE), a modular compound AI system leveraging multiple expert LLMs. CoE leverages a router to dynamically select the most appropriate expert for a given input, enabling efficient utilization of resources and improved performance. We formulate the general problem of training a CoE and discuss inherent complexities associated with it. We propose a two-step routing approach to address these complexities that first uses a router to classify the input into distinct categories followed by a category-to-expert mapping to obtain desired experts. CoE offers a flexible and cost-effective solution to build compound AI systems. Our empirical evaluation demonstrates the effectiveness of CoE in achieving superior performance with reduced computational overhead. Given that CoE comprises of many expert LLMs it has unique system requirements for cost-effective serving. We present an efficient implementation of CoE leveraging SambaNova SN40L RDUs unique three-tiered memory architecture. CoEs obtained using open weight LLMs Qwen/Qwen2-7B-Instruct, google/gemma-2-9b-it, google/gemma-2-27b-it, meta-llama/Llama-3.1-70B-Instruct and Qwen/Qwen2-72B-Instruct achieve a score of 59.4 with merely 31 billion average active parameters on Arena-Hard and a score of 9.06 with 54 billion average active parameters on MT-Bench.

  • 11 authors
·
Dec 2, 2024

A Systematic Study of In-the-Wild Model Merging for Large Language Models

Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving performance. However, it remains unclear whether the advantages reported for settings where all merged experts have distinct roles and are tuned on clearly separated tasks also hold in settings where the merged experts do not have clearly distinct roles, but are trained on overlapping or even conflicting objectives. To evaluate this setting, we present a large-scale, systematic evaluation of "in-the-wild" model merging of heterogeneous experts, that may have been trained on overlapping or conflicting objectives. Concretely, we evaluate six state-of-the-art merging methods, including recent subspace methods, across four open-weight LLMs, twelve fine-tuned checkpoints per base model, and sixteen standard LLM benchmarks. Evaluating through standardized benchmarks, we measure both the probability that a model merged from a heterogeneous set of experts outperforms the base model and we measure relative gains over the best individual checkpoint. Our results show that the oldest and simplest method, Task Arithmetic, is the only approach that reliably yields performance gains on LLMs in this "in-the-wild" setting. Other interference-aware and subspace merging methods typically do not result in notable improvements over the base model. Our findings indicate that current merging techniques mostly do not enable extracting useful weight updates from heterogeneous and potentially conflicting versions. This motivates the design of LLM-specific merging algorithms and merging-aware fine-tuning methods.

  • 3 authors
·
Mar 28

Evaluating and Benchmarking the System One Model Jev

Jev is a commercial System One model from TypeSafe AI that does not generate text: given a state and typed questions, it returns a choice from fixed options, a position on a rubric, or the probability that a statement is true, with probabilities the vendor describes as calibrated. Such models target small decisions in information access pipelines, such as routing queries, checking grounding, moderating content, or rating against a rubric. We evaluate Jev (jev-1.13.0) zero-shot on 37 datasets spanning classification, routing, natural language inference, reading comprehension, commonsense reasoning, moderation, legal clause analysis and rubric scoring, with one frozen template per dataset and full evaluation splits: 346,009 requests for under USD 10. For reference, we score Qwen3.8-27B and Gemma-4-E4B on identical requests via their exact next-token probabilities over the options. Jev reaches 95-99% accuracy on IMDB, SST-2, HellaSwag and ARC and 86.7% on Belebele across 122 languages. It beats Qwen on 27 of 37 datasets, with none of Qwen's nine leads outside the bootstrap intervals, and Gemma on all 37. All three models degrade on low-resource languages, fine-grained or noisy labels, and rubric-based quality judgments. Jev's choice probabilities are well calibrated and support selective prediction. Binary probabilities rank well but are poorly placed relative to a fixed 0.5 threshold; thresholds tuned on training data raise micro-F1 on UNFAIR-ToS from 0.50 to 0.75. Jev answers MMLU's calculation-heavy questions more accurately than other MMLU questions (94% vs. 91%), whereas both open models, and all three on C-Eval, find them harder. Rotating the options leaves Jev's accuracy unchanged and withholding the question drops it to near chance, ruling out shallow memorization but not memorized question-answer pairs. We release the code, harness and all raw responses.

  • 3 authors
·
Sep 28

LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics

Off-the-shelf large language models (LLMs) are increasingly used to automate text annotation, yet their effectiveness remains underexplored for underrepresented languages and specialized domains where the class definition requires subtle expert understanding. We investigate LLM-based annotation for a novel legal NLP task: identifying the presence and sentiment of credibility assessments in asylum decision texts. We introduce RAB-Cred, a Danish text classification dataset featuring high-quality, expert annotations and valuable metadata such as annotator confidence and asylum case outcome. We benchmark 21 open-weight models and 30 system-user prompt combinations for this task, and systematically evaluate the effect of model and prompt choice for zero-shot and few-shot classification. We zoom in on the errors made by top-performing models and prompts, investigating error consistency across LLMs, inter-class confusion, correlation with human confidence and sample-wise difficulty and severity of LLM mistakes. Our results confirm the potential of LLMs for cost-effective labeling of asylum decisions, but highlight the imperfect and inconsistent nature of LLM annotators, and the need to look beyond the predictions of a single, arbitrarily chosen model. The RAB-Cred dataset and code are available at https://github.com/glhr/RAB-Cred

Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models

Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that validate users rather than prioritize factual accuracy. While prior work has established that sycophancy poses risks to AI safety and alignment, the relationship between specific personality traits of adopted personas and the degree of sycophantic behavior remains unexplored. We present a systematic investigation of how persona agreeableness influences sycophancy across 13 small, open-weight language models ranging from 0.6B to 20B parameters. We develop a benchmark comprising 275 personas evaluated on NEO-IPIP agreeableness subscales and expose each persona to 4,950 sycophancy-eliciting prompts spanning 33 topic categories. Our analysis reveals that 9 of 13 models exhibit statistically significant positive correlations between persona agreeableness and sycophancy rates, with Pearson correlations reaching r = 0.87 and effect sizes as large as Cohen's d = 2.33. These findings demonstrate that agreeableness functions as a reliable predictor of persona-induced sycophancy, with direct implications for the deployment of role-playing AI systems and the development of alignment strategies that account for personality-mediated deceptive behaviors.

  • 3 authors
·
Apr 11

An Independent Safety Evaluation of Kimi K2.5

Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying safety evaluation. In this work, we conduct a preliminary safety assessment of Kimi K2.5 focusing on risks likely to be exacerbated by powerful open-weight models. Specifically, we evaluate the model for CBRNE misuse risk, cybersecurity risk, misalignment, political censorship, bias, and harmlessness, in both agentic and non-agentic settings. We find that Kimi K2.5 shows similar dual-use capabilities to GPT 5.2 and Claude Opus 4.5, but with significantly fewer refusals on CBRNE-related requests, suggesting it may uplift malicious actors in weapon creation. On cyber-related tasks, we find that Kimi K2.5 demonstrates competitive cybersecurity performance, but it does not appear to possess frontier-level autonomous cyberoffensive capabilities such as vulnerability discovery and exploitation. We further find that Kimi K2.5 shows concerning levels of sabotage ability and self-replication propensity, although it does not appear to have long-term malicious goals. In addition, Kimi K2.5 exhibits narrow censorship and political bias, especially in Chinese, and is more compliant with harmful requests related to spreading disinformation and copyright infringement. Finally, we find the model refuses to engage in user delusions and generally has low over-refusal rates. While preliminary, our findings highlight how safety risks exist in frontier open-weight models and may be amplified by the scale and accessibility of open-weight releases. Therefore, we strongly urge open-weight model developers to conduct and release more systematic safety evaluations required for responsible deployment.

  • 15 authors
·
Apr 2

Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that actually influence their outputs), a property that prior evaluations have examined in only two proprietary models, finding acknowledgment rates as low as 25% for Claude 3.7 Sonnet and 39% for DeepSeek-R1. To extend this evaluation across the open-weight ecosystem, this study tests 12 open-weight reasoning models spanning 9 architectural families (7B-685B parameters) on 498 multiple-choice questions from MMLU and GPQA Diamond, injecting six categories of reasoning hints (sycophancy, consistency, visual pattern, metadata, grader hacking, and unethical information) and measuring the rate at which models acknowledge hint influence in their CoT when hints successfully alter answers. Across 41,832 inference runs, overall faithfulness rates range from 39.7% (Seed-1.6-Flash) to 89.9% (DeepSeek-V3.2-Speciale) across model families, with consistency hints (35.5%) and sycophancy hints (53.9%) exhibiting the lowest acknowledgment rates. Training methodology and model family predict faithfulness more strongly than parameter count, and keyword-based analysis reveals a striking gap between thinking-token acknowledgment (approximately 87.5%) and answer-text acknowledgment (approximately 28.6%), suggesting that models internally recognize hint influence but systematically suppress this acknowledgment in their outputs. These findings carry direct implications for the viability of CoT monitoring as a safety mechanism and suggest that faithfulness is not a fixed property of reasoning models but varies systematically with architecture, training method, and the nature of the influencing cue.

  • 1 authors
·
Mar 23 2

Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks

As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are routinely accompanied by comprehensive system cards, open-weight models receive less scrutiny regarding frontier risks. To address this gap, we present an independent safety evaluation of DeepSeek V4.1 Flash-1017, the latest version of V4.1 Flash that departs from V4 with a new architecture, scaled-up training, and strong agentic capabilities. Drawing on the EU General-Purpose AI Code of Practice, we evaluate the model across 34 benchmarks, including 5 in-house suites, spanning evaluation integrity, loss of control, and harmful manipulation. Conforming to the AEF-1 standard, we compare V4.1 Flash-1017 against V4.1 Flash, earlier DeepSeek V4 models, and leading closed-source systems (GPT-6 Astra, GPT-5.6 Sol, and Gemini 3.8 Flash). Overall, V4.1 Flash-1017 shows substantial safety improvements over the V4 generation and approaches or matches leading closed-source baselines on several dimensions, while still exhibiting notable behaviors that warrant continued attention. Building on our findings, we highlight three key observations and recommendations. First, because safety can shift and even regress across minor updates, developers should integrate safety evaluation into incremental releases. Second, as final-turn outputs and end-state checks alone cannot reliably detect loss-of-control behaviors, deployments require process-level observability across both reasoning traces and action logs. Third, because public benchmarks elicit strong evaluation awareness and face data contamination risks, developing private benchmarks is essential for trustworthy frontier evaluation.

FangcunAI Fangcun AI
·
Oct 25 2

Serialisation Strategy Matters: How FHIR Data Format Affects LLM Medication Reconciliation

Medication reconciliation at clinical handoffs is a high-stakes, error-prone process. Large language models are increasingly proposed to assist with this task using FHIR-structured patient records, but a fundamental and largely unstudied variable is how the FHIR data is serialised before being passed to the model. We present the first systematic comparison of four FHIR serialisation strategies (Raw JSON, Markdown Table, Clinical Narrative, and Chronological Timeline) across five open-weight models (Phi-3.5-mini, Mistral-7B, BioMistral-7B, Llama-3.1-8B, Llama-3.3-70B) on a controlled benchmark of 200 synthetic patients, totalling 4,000 inference runs. We find that serialisation strategy has a large, statistically significant effect on performance for models up to 8B parameters: Clinical Narrative outperforms Raw JSON by up to 19 F1 points for Mistral-7B (r = 0.617, p < 10^{-10}). This advantage reverses at 70B, where Raw JSON achieves the best mean F1 of 0.9956. In all 20 model and strategy combinations, mean precision exceeds mean recall: omission is the dominant failure mode, with models more often missing an active medication than fabricating one, which changes how clinical safety auditing priorities should be set. Smaller models plateau at roughly 7-10 concurrent active medications, leaving polypharmacy patients, the patients most at risk from reconciliation errors, systematically underserved. BioMistral-7B, a domain-pretrained model without instruction tuning, produces zero usable output in all conditions, showing that domain pretraining alone is not sufficient for structured extraction. These results offer practical, evidence-based format recommendations for clinical LLM deployment: Clinical Narrative for models up to 8B, Raw JSON for 70B and above. The complete pipeline is reproducible on open-source tools running on an AWS g6e.xlarge instance (NVIDIA L40S, 48 GB VRAM).

  • 1 authors
·
Apr 21

Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the 31-bit KoalaBear prime. The proof batches zerochecks and LogUp-GKR lookups into one sumcheck per domain, and commits to every witness tensor and weight in one multilinear commitment built from Reed-Solomon codes, BLAKE3 Merkle trees and a mixed-length BaseFold opening. The prover streams the model layer by layer on one GPU. On one NVIDIA RTX PRO 6000 Blackwell GPU, Sable proves all 64 layers of Qwen2.5-32B in 92.5 s for 4,096 tokens and 398 s for 16,384 tokens, and covers Qwen3-32B and the mixture-of-experts Qwen3-30B-A3B (4,096 tokens in 121.8 and 84.7 s). A proof costs 41 to 50 times the serving time, or 6.4 cents per 4,096-token request at public GPU prices, and 40 to 64 times less time per parameter and token than zkLLM. On WikiText-2, F_O's greedy token matches the BF16 model's at 86.3% of positions; on Qwen3, F_O is within 1.6 points of BF16 on MMLU and 1.7 points on GSM8K. A verifier with a compiled core checks a proof on one CPU core in 19 to 56 s. In the random-oracle model, the interactive proof has round-by-round soundness error 2^-103. The proof is not zero-knowledge, so the system targets open-weight models. Code: https://github.com/moonmath-ai/Sable

MoonMath-ai MoonMath.ai
·
Nov 9 4

Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance

We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding when to interrupt, and how to coach. However, progress is limited by the absence of large-scale, cross-domain benchmarks that reflect realistic conditions, particularly the common case in which users deviate from the expected step sequence. We address this gap with four contributions: (1)~we release EgoProactive, a large-scale wearable-egocentric dataset for proactive procedural assistance with explicit Out-of-Plan (OOP) annotations and recovery steps; (2)~we augment five established benchmarks (Ego4D, EPIC-KITCHENS, EgoExo4D, HoloAssist, HowTo100M) into Pro\textsuperscript{2Bench} under a unified proactive-guidance schema; (3)~we propose a decoupled planner--interaction architecture specialized for procedural state, visual cues, and recovery injection; (4)~we introduce a post-training recipe that transfers across model families, validated by cross-backbone replication on Llama~4 and Qwen-3.6-VL. In extensive experiments, our trained Llama-4 system substantially improves objective intervention quality over strong proprietary baselines (Claude Opus~4.6, Gemini~3.1~Pro, GPT~5.2) and open-weight baselines (Qwen3~VL~235B) baselines across all six datasets. Oracle-plan experiments further show that, when plan quality is controlled, the trained duplex model produces high-quality guidance and large gains on Out-of-Plan recovery.

  • 16 authors
·
Jun 2

EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding

We introduce EgoSAT, the first comprehensive benchmark for egocentric video reasoning in streaming settings, designed to evaluate the capabilities of modern vision-language models (VLMs). The benchmark targets streaming interaction understanding, where video frames arrive sequentially and models must continuously interpret evolving visual context. EgoSAT unifies several previously distinct tasks within a single streaming framework. In this formulation, queries about completed events correspond to retrospective reasoning, queries about ongoing activities require online understanding, and queries about future actions involve prospective anticipation. This unified setting requires models to reason about the past, present, and future while operating under the constraint that only previously observed frames are available. EgoSAT contains 1,997 unique videos spanning 165 hours of egocentric footage and around 4,800 high-quality question-answer pairs, carefully designed to probe reasoning across varying temporal contexts. Using this benchmark, we evaluate a diverse set of both open-weight and closed-weight VLMs, providing a systematic assessment of their ability for streaming interaction understanding. By distinguishing answerability and conducting diagnostics on confidence of models, we find existing models not only struggle with prospective and retrospective modeling, but also exhibit severe mis-calibration: confidence often fails to track inherent answerability, leading to dangerous "confidently wrong" behaviors. Project page: https://leiyj23.github.io/EgoSAT/

  • 6 authors
·
Jun 22

Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models

Despite increasing discussions on open-source Artificial Intelligence (AI), existing research lacks a discussion on the transparency and accessibility of state-of-the-art (SoTA) Large Language Models (LLMs). The Open Source Initiative (OSI) has recently released its first formal definition of open-source software. This definition, when combined with standard dictionary definitions and the sparse published literature, provide an initial framework to support broader accessibility to AI models such as LLMs, but more work is essential to capture the unique dynamics of openness in AI. In addition, concerns about open-washing, where models claim openness but lack full transparency, has been raised, which limits the reproducibility, bias mitigation, and domain adaptation of these models. In this context, our study critically analyzes SoTA LLMs from the last five years, including ChatGPT, DeepSeek, LLaMA, and others, to assess their adherence to transparency standards and the implications of partial openness. Specifically, we examine transparency and accessibility from two perspectives: open-source vs. open-weight models. Our findings reveal that while some models are labeled as open-source, this does not necessarily mean they are fully open-sourced. Even in the best cases, open-source models often do not report model training data, and code as well as key metrics, such as weight accessibility, and carbon emissions. To the best of our knowledge, this is the first study that systematically examines the transparency and accessibility of over 100 different SoTA LLMs through the dual lens of open-source and open-weight models. The findings open avenues for further research and call for responsible and sustainable AI practices to ensure greater transparency, accountability, and ethical deployment of these models.(DeepSeek transparency, ChatGPT accessibility, open source, DeepSeek open source)

  • 3 authors
·
Feb 21, 2025

Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX

High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing the capabilities of robot algorithms. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that can synthesize data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the limits of aerial-robotics algorithm development, from model-based to data-driven methods, gradient-based to sampling-based approaches, and single-agent to multi-agent systems. Compared to existing state-of-the-art drone simulators, it achieves speeds more than an order of magnitude faster for a single drone and can simulate thousands of swarms of 4000 drones each. Real-world experiments show Crazyflow supports both analytical-gradient-based policy learning, achieving sub-centimeter trajectory tracking accuracy without domain randomization, and sampling-based obstacle avoidance at speeds exceeding half a billion steps per second. Breaking the traditional train-then-deploy paradigm, we show that its unprecedented speed even enables in-flight reinforcement learning; we demonstrate this by throwing a physical drone into the air and training a recovery policy from scratch in 0.38 seconds, successfully stabilizing the drone. Crazyflow supports multiple levels of simulation abstraction, is directly compatible with all open-source Crazyflie models, and enables rapid reconfiguration across custom drone platforms and applications by providing a light-weight system identification pipeline. By pushing accuracy, speed, and differentiability simultaneously, Crazyflow serves as an open-source resource for synthetic data generation, with emerging capabilities for large-scale parallelization for online, in-execution learning and optimization, opening the door to novel algorithm development.

  • 6 authors
·
Jun 4

AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving

Optimizing Large Language Model (LLM) inference in production systems is increasingly difficult due to dynamic workloads, stringent latency/throughput targets, and a rapidly expanding configuration space. This complexity spans not only distributed parallelism strategies (tensor/pipeline/expert) but also intricate framework-specific runtime parameters such as those concerning the enablement of CUDA graphs, available KV-cache memory fractions, and maximum token capacity, which drastically impact performance. The diversity of modern inference frameworks (e.g., TRT-LLM, vLLM, SGLang), each employing distinct kernels and execution policies, makes manual tuning both framework-specific and computationally prohibitive. We present AIConfigurator, a unified performance-modeling system that enables rapid, framework-agnostic inference configuration search without requiring GPU-based profiling. AIConfigurator combines (1) a methodology that decomposes inference into analytically modelable primitives - GEMM, attention, communication, and memory operations while capturing framework-specific scheduling dynamics; (2) a calibrated kernel-level performance database for these primitives across a wide range of hardware platforms and popular open-weights models (GPT-OSS, Qwen, DeepSeek, LLama, Mistral); and (3) an abstraction layer that automatically resolves optimal launch parameters for the target backend, seamlessly integrating into production-grade orchestration systems. Evaluation on production LLM serving workloads demonstrates that AIConfigurator identifies superior serving configurations that improve performance by up to 40% for dense models (e.g., Qwen3-32B) and 50% for MoE architectures (e.g., DeepSeek-V3), while completing searches within 30 seconds on average. Enabling the rapid exploration of vast design spaces - from cluster topology down to engine specific flags.

  • 21 authors
·
Jan 8

OpenS2S: Advancing Open-Source End-to-End Empathetic Large Speech Language Model

Empathetic interaction is a cornerstone of human-machine communication, due to the need for understanding speech enriched with paralinguistic cues and generating emotional and expressive responses. However, the most powerful empathetic LSLMs are increasingly closed off, leaving the crucial details about the architecture, data and development opaque to researchers. Given the critical need for transparent research into the LSLMs and empathetic behavior, we present OpenS2S, a fully open-source, transparent and end-to-end LSLM designed to enable empathetic speech interactions. Based on our empathetic speech-to-text model BLSP-Emo, OpenS2S further employs a streaming interleaved decoding architecture to achieve low-latency speech generation. To facilitate end-to-end training, OpenS2S incorporates an automated data construction pipeline that synthesizes diverse, high-quality empathetic speech dialogues at low cost. By leveraging large language models to generate empathetic content and controllable text-to-speech systems to introduce speaker and emotional variation, we construct a scalable training corpus with rich paralinguistic diversity and minimal human supervision. We release the fully open-source OpenS2S model, including the dataset, model weights, pre-training and fine-tuning codes, to empower the broader research community and accelerate innovation in empathetic speech systems. The project webpage can be accessed at https://casia-lm.github.io/OpenS2S

  • 11 authors
·
Jul 7, 2025

Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that write and refine their own executable skills as code. This survey organises the field around that axis of weights versus skills. Its central analytical contribution is a deep-dive that arranges code-as-policy methods by their degree of self-improvement, from zero-shot program synthesis, through closed-loop self-repair and persistent skill memory, to the sparsely populated cell in which execution feedback, skill memory, and evolutionary search combine into one open-ended loop; only a few very recent systems (for example ASPIRE, ENPIRE, and RoboClaw) occupy that cell. We map the complementary "skills" pole, from unsupervised reinforcement-learning skill discovery to large-language-model skill libraries, and show that the word "skill" is used in at least five distinct senses, of which only the code sense self-improves without gradient updates. We then connect the taxonomy to the emerging skill economy: commercial robot-skill marketplaces now distribute one-tap skills across robots but ship only static playback, which surfaces open problems of adaptation, cross-embodiment portability, provenance, safety verification, composition, and standardisation. This is a deliberately focused survey. Rather than cataloguing the field exhaustively, it examines 77 representative systems across six technique families through one taxonomy and a set of contrast tables, and it supplies operational definitions of the self-improvement mechanisms together with a statement of what each family cannot do.

  • 6 authors
·
Aug 2 2

ModHiFi: Identifying High Fidelity predictive components for Model Modification

Open weight models, which are ubiquitous, rarely provide access to their training data or loss function. This makes modifying such models for tasks such as pruning or unlearning constrained by this unavailability an active area of research. Existing techniques typically require gradients or ground-truth labels, rendering them infeasible in settings with limited computational resources. In this work, we investigate the fundamental question of identifying components that are critical to the model's predictive performance, without access to either gradients or the loss function, and with only distributional access such as synthetic data. We theoretically demonstrate that the global reconstruction error is linearly bounded by local reconstruction errors for Lipschitz-continuous networks such as CNNs and well-trained Transformers (which, contrary to existing literature, we find exhibit Lipschitz continuity). This motivates using the locally reconstructive behavior of component subsets to quantify their global importance, via a metric that we term Subset Fidelity. In the uncorrelated features setting, selecting individual components via their Subset Fidelity scores is optimal, which we use to propose ModHiFi, an algorithm for model modification that requires no training data or loss function access. ModHiFi-P, for structured pruning, achieves an 11% speedup over the current state of the art on ImageNet models and competitive performance on language models. ModHiFi-U, for classwise unlearning, achieves complete unlearning on CIFAR-10 without fine-tuning and demonstrates competitive performance on Swin Transformers.