Skip to content

Author

Yu Pei

We have 2 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Trajectory-Guided Fault Localization for Agent Skill Evolution

Agent skills provide reusable guidance for code agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort of skill refinement, recent approaches use LLMs to generate revisions from execution feedback. However, grounding these revisions in explicit behavioral evidence remains c...

Yu Ge, Lin-Na Xie, Zhong Li et al. · 0 citations
Open access Jun 2026

Spectrum-Based Failure Attribution for Multi-agent Systems

FAMAS is the first spectrum-based failure attribution approach for MASs and proposes a novel suspiciousness formula tailored to MASs, which integrates two key factor groups, namely the agent behavior group and the action behavior group, to account for the agent activation patterns and action activation patterns within...

Yu Ge, Linna Xie, Zhong Li et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.