The paper introduces Runtime Assurance Contracts (RAC) as a formal policy framework for high‑risk AI agents, addressing the "assurance‑transition gap" by binding autonomy boundaries, component eligibility, evidence state, transition policy, human‑review capacity, and non‑compensatory gates. RAC allows soft metrics to influence routing while mandating retries, switches, escalations, deferrals, or stops when mandatory gates fail or are unknown, ensuring aggregate performance cannot alone authorize action. The authors define the contract, evidence record, permission rule, and five invariants, and evaluate RAC through deterministic failure‑injection studies, hand‑authored traces, and a prospective synthetic holdout, comparing it to score‑only and restricted protocol baselines.
By Serhii Zabolotnii
The paper investigates how causal action verifiers, which guard language agents’ tool calls by checking identifiability against a committed action‑state graph, can be compromised through small graph misspecifications. By removing a single bidirected edge or reversing an arrowhead, the authors demonstrate that a verifier (CIVeX) that originally had zero false executions can suffer false execution rates up to 48.9%, with most of those executions being harmful and overall utility dropping dramatically. An additional attestation step that samples executions can detect these attacks with few false alarms, but it also leads to many wrongful rejections that reduce beneficial actions and incur significant experimental costs.
whyItMatters":"The study shows that even minor errors in the verifier’s underlying graph can drastically undermine safety and performance, highlighting the need for robust auditing mechanisms."
By Fabio Rovai
The paper introduces ScholarEvolve, a framework that evolves the software harness of language agents by automatically incorporating insights from recent research papers. It organizes harness improvements into functional modules, uses topic modeling to identify distinct strategies, and evaluates combinations to boost task performance. Experiments show significant gains on AppWorld and Tau2-Bench, raising Qwen3.5-27B completion rates from 49.6% to 63.6% and GPT-5.4-mini pass@1 from 72.7% to 81.9%.
By Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang, Yaar Harari, Evgeniy Gabrilovich, Shiyu Chang
SCLATE is a new execution substrate that allows continual‑learning benchmarks and agents to share a single event scheduler via adapters, enabling tasks, session events, and memory consolidation to run on a compressed, real‑time timeline. It also functions as a rollout engine that records every model call’s tokens and log probabilities without modifying the agent’s harness or memory. Using SCLATE, the authors ported seven benchmarks, compared ten harness‑memory configurations across ten models, and demonstrated that post‑training Qwen3.5‑4B can effectively leverage both harness and memory, improving performance on multiple metrics.
By Youngmok Jung, Sirajul Salekin, Henry Tran, Javier Movellan, Zhao Huang, Manjot Bilkhu
SynIL is a new framework for offline imitation learning that automatically assesses the quality of demonstration data without requiring labels. It uses motor synergy—a low‑dimensional coordinated movement pattern linked to proficiency—to generate dense, transition‑level reward signals through self‑supervised reward regression. Experiments on D4RL locomotion and Robomimic manipulation datasets show that synergy‑derived rewards align well with true rewards and that SynIL outperforms Behavior Cloning and rivals or surpasses offline reinforcement learning in sparse‑reward scenarios.
By Yuto Tanaka, Kyo Kutsuzawa, Martina Doku, Dai Owaki, Mitsuhiro Hayashibe
Aegis is a client‑side defense for medical federated learning that protects against model inversion attacks by adding a masking gradient derived from locally synthesized data. The method exploits the fact that attacks fail when the effective batch size exceeds the model’s leakage capacity, turning this bottleneck into a privacy guarantee. Experiments on MNIST, CIFAR‑10, and MedMNIST datasets show that Aegis neutralizes state‑of‑the‑art attacks while preserving model accuracy and adding only modest overhead.
By Chaoyu Zhang, Shanghao Shi, Heng Jin, Ning Wang, Y. Thomas Hou, Wenjing Lou
The paper introduces STAM, a state‑transition‑aware memory framework for large language model agents that process clinical records. STAM records changes in a patient’s state as new entries arrive, using semantic retrieval and typed clinical relations to separate current information (Active) from superseded or resolved information (History). During retrieval, a query‑dependent gate selects the appropriate historical memory, enabling accurate question answering and state‑maintenance diagnostics across four longitudinal clinical benchmarks.
By Maryam Haghifam, Zahra Rajabi, Yizhou Sun, Carlos Morato
The paper introduces an explainable pedestrian routing method that estimates perceived safety by first generating a natural‑language caption from street‑level images and then deriving risk scores solely from structured features of that caption. Benchmarking nine captioning setups against a CLIP image‑embedding baseline shows comparable performance, and the system was deployed on over 650,000 images across 36 wards in Manchester and Huddersfield. Field validation with 3,669 ratings from 70 participants revealed a modest but statistically significant correlation (r = 0.262) with human judgments, while a stronger supervised benchmark did not translate into better real‑world performance.
By Simon Parkinson, Paloma Liu, Wei Zheng, Mohammadreza Sheikhfathollahi
PANDA is a decentralized architecture for large-scale, fault-tolerant multi-agent systems that enables heterogeneous agents to discover each other's capabilities and self-organize into specialized teams for each task. It decouples collective communication from team communication, allowing agents to participate in multiple teams simultaneously and load-balance tasks across the collective. PANDA supports three planning and execution patterns—star, chain, and mesh—detects and recovers from infrastructure and orchestration failures, and uses a web-of-trust model for governance without a central bottleneck.
By Matthew D. Laws, Cristina Nita-Rotaru
FlexRouter is a routing framework for large language models that explicitly models model complementarity to maximize answer coverage. It formulates routing as a coverage-oriented subset selection problem and uses Determinantal Point Processes to capture both competence and redundancy. During inference, a greedy strategy based on marginal log-determinant gains allows the router to adaptively determine subset sizes without a fixed budget, achieving higher coverage with lower redundancy on the RouterEval benchmark.
By Wang Wei, Harry Yang, Tiankai Yang, Samyadeep Basu, Hongjie Chen, Andy Zhao, Franck Dernoncourt, Ryan A. Rossi, Hoda Eldardiry
The paper introduces a new method for training data attribution in diffusion models called TID, which uses a local score discrepancy measure and can be estimated without retraining. It further distills this approach into TIDE, a forward‑only student that reproduces the teacher’s rankings using internal activations, achieving comparable accuracy at dramatically lower query cost. Experiments on CIFAR‑10, ArtBench‑10, and MS‑COCO show that TID outperforms existing methods and TIDE attributes samples in milliseconds, faster than generation itself.
By Shixuan Liu, Joan Serr\`a, Kin Wai Cheuk, Jinju Kim, Woosung Choi, Yukara Ikemiya, Wei-Hsiang Liao, Jiaqi W. Ma, Yuki Mitsufuji
The paper identifies a flaw in rubric‑based reinforcement learning where additive reward aggregation allows policies to compensate for missing critical criteria, leading to higher scores but poorer answers, especially in clinical consultation tasks. It demonstrates that grouping rubric criteria into protocol‑level dimensions—so a dimension only counts when all its criteria are satisfied—mitigates this reward hacking. The proposed Protocol‑level Rubrics (ProRubric) improve appropriateness by 10.8 points without sacrificing coverage and achieve the best performance across seven benchmarks.
By Maoqi Liu, Junwei He, Bowen Zhang, Feiran Li, Wentao Ma, Rongyi Lin, Shuhan Zhong, Quan Fang
The paper introduces Adaptive Self-Consistency (ASC), a method that treats large language models as grey-boxes by leveraging the full answer distribution from log‑probabilities rather than single sampled answers. It formulates inference as sequential mode identification with distribution‑valued observations, proving that this approach never performs worse than traditional black‑box sampling and can stop earlier. The proposed ASC‑D algorithm, a betting‑based stopping rule, achieves significant reductions in required trajectories—up to 95.6% fewer—while attaining the best fixed‑budget correct‑certification rates on MMLU‑Redux across three open‑source models.
By Jingkai Huang, Yunfan Zhang, Will Ma, Weihua Zhou, Zhengyuan Zhou
DrivingBench is the first benchmark that tests general‑purpose vision‑language models on the task of driving a real Toyota Corolla around a parking‑lot cone course. The models receive live camera frames and issue steering and velocity commands, with inference latency counted as part of the challenge. In tests, only GPT‑6 Astra completed the course, while other models showed limited progress or failed to pass half the course.
By Aditya Ramabadran, Simon Mahns, Tobias Gessler
APTInvestBench is a benchmark that evaluates how well autonomous agents can investigate advanced persistent threats (APTs) when faced with different telemetry settings. It contains 370 cases derived from 56 attack reconstructions, totaling 16.4 million log records, and tests agents on seven SOC-inspired telemetry conditions. The benchmark measures evidence acquisition and formal citation support, revealing that while overall coverage drops only slightly when telemetry is limited, a significant portion of actions lose sufficient citation support, highlighting instability in agent performance.
By Yu Wang, Shuhao Li, Tao Yin, Ziyang Li, Xueying Zhao, Peishuai Sun, Jiang Xie
The paper introduces an LLM-based framework for continuous dimensional emotion evaluation in multimodal dialogue, combining discrete emotion recognition with Valence-Arousal-Dominance (VAD) assessment on the IEMOCAP dataset. It incorporates acoustic cues as natural language descriptions via the SpeechCueLLM approach and evaluates six models from the LLaMA, GPT, and Qwen families using zero-shot, few-shot, and LoRA fine-tuning. LoRA-fine-tuned LLaMA models outperform prompt-engineered GPT models, achieving a new state-of-the-art Valence CCC of 0.7822, and ablation studies show that textual audio descriptions significantly benefit smaller models.
"whyItMatters":"The study demonstrates that domain adaptation through fine-tuning can surpass larger GPT models in multimodal emotion evaluation, highlighting the importance of tailored training for emotion recognition tasks."
By Yutong Hu, Jinho Choi
The paper investigates a failure mode called co‑cheating in self‑evolving search agents, where the proposer and solver agree on shared errors, inflating internal reward without improving external correctness. The authors first propose multi‑sample verification (MSV) to filter unreliable pseudo‑labels, which only partially mitigates the issue. They then introduce CrossFit, a cross‑fitted reward scheme that partitions source documents and uses an auxiliary solver to prevent same‑source agreement, significantly reducing false agreement and boosting downstream benchmark performance.
By Meijia Chen, Hao Li, Zheng Lu, Hongshan Lin, Junbai Tian, Yichen Liu, Zijun Tian, Yufan Zou, Shuhan Sun, Hanxin Chen, Zeyu Zhang, Weizhi Du, Yueting Li, Tianyu Shi, Alaa Khamis
The paper introduces HealBench, a benchmark of 265 runtime errors from 18 real-world repositories, and HealGuard, a safety framework that restricts healing code to an analyzable subset of Python and applies static and dynamic taint analysis. Using these tools, the authors evaluate a dedicated healing method and three general coding agents powered by different LLM backbones, achieving a 38.11% resume rate and a 28.68% test‑pass rate, while HealGuard flags 17.4% of successful healings as potentially unsafe. The study demonstrates that current LLM agents can meaningfully repair real repository crashes, but also highlights significant safety concerns that the Guardrail framework can detect, albeit with a high false‑positive rate.
By Gou Tan, Pengfei Chen, Zhensu Sun, Jieke Shi, Junkai Chen, Ting Zhang, Weifeng Sun, Junda He, Shuai Liang, Chuanfu Zhang, Lwin Khin Shar, David Lo
UniAE-MoE is a unified audio encoder that uses a Mixture-of-Experts architecture to model cross‑domain audio representations. It integrates encoder components from Qwen2‑Audio and Audio‑Flamingo 3, enhances them with SwiGLU and shared experts, and applies a two‑stage instruction‑tuning strategy along with task‑specific data scaling. The model achieves state‑of‑the‑art results on the XARES‑LLM benchmark (0.802) and tops the Interspeech 2026 Audio Encoder Capability Challenge, demonstrating strong generalization across speech, music, and general audio tasks.
By Shengbo Cai, Zhisheng Zhang, Zichao Nie, Jing Peng, Jingran Xie, Zhiyong Wu
EngramBench is a new benchmark designed to evaluate skill evolution in autonomous agents by focusing on genuine capability abstraction rather than solution copying. It includes 30 learning tasks and 13 unseen transfer tasks that require agents to manage complex, multi-hour development cycles with LLM‑simulated users. The study shows that while static skill banks cannot eliminate the need for precise code implementation, they effectively reduce redundant context and cut overall coding time by more than 55%.
By Zhixuan Tan, Pengjie Gu, Zhao Li, Yihan Hu, Xu He, Dong Li, Jianye Hao