Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking ac...
Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaking correct behavior. Existing benchmarks do not systematically distinguish documentation repair, script repair, and preservation when evaluating skill s...
Yuxuan Liu, Hao-Ran Li, Yu-Hao Zhang et al.· 0 citations
Noise-Aware Verbal Confidence CAlibration Rules are proposed to provide a principled foundation for resolving overconfidence under noise and NOVA, a noise-aware calibration framework that synthesizes supervision from ~2K HotpotQA examples guided by these rules.
Real-world decision-making often involves uncertainty expressed in linguistic rather than numerical terms, and Prospect Theory (PT) provides a classic framework for modeling human behavior under such uncertainty. Although recent studies have developed frameworks to estimate PT parameters for Large Language Models (LLMs...
Rui Wang, Qi-Han Lin, Jiayu Liu et al.· 2 citations
This work introduces EAVer, an End-to-end Agentic Verifier that learns to control the complete response-level verification workflow as a unified policy, and construct 794 bidirectional same-trajectory preference pairs that keep claim grouping, search, and evidence fixed, enabling decision-focused Direct Preference Opti...
Ke-Ning Zheng, Ao-Ying Zheng, Zhi-Gang Chang et al.· 0 citations
UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three information-flow patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficien...
Evaluated across three main benchmarks, two domain-specific studies, and six LLMs, SkillRevise substantially outperforms one-shot baselines, and the revised skills transfer across both executors and task environments, suggesting that SkillRevise captures reusable procedural knowledge beyond any single executor.
Yuxuan Liu, Zhao-Chen Su, Lin Xie et al.· arXiv.org· 17 citations
Consistent gains over DVD on LVBench, Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V, and proposes PACE (Progressive Acquisition of Critical Evidence), a factor-guided framework for long-video evidence acquisition.
Bai-Xuan Xu, Yinyui Xu, Tianshi ZHENG et al.· 1 citation
Results indicate that MultivationBench presents a significant challenge: all tested models struggle to maintain consistent motivation reasoning across sequential contexts, revealing a critical disconnect between static recognition capabilities and the dynamic reasoning essential for human-like social understanding.
This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another.
Qing Zong, Jiayu Liu, Junhao Shen et al.· 0 citations
Overall, persistent skill self-evolution is better understood as sparse, validation-filtered search with model- and benchmark-dependent returns, rather than steady improvement from additional rounds.
Yuxuan Liu, Zhaochen Su, Yuhao Zhang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
