Skip to content

TRACE-MAS: Diagnosing and repairing collaboration failures in multi-agent systems

TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems

arXiv: 其他 AI 安全论文· arXiv:2611.23362· Zekai Chen, Yihan Sun, Xunkai Li, Xun Wu, Xinmo Jin, Yinlin Zhu, Haodong Lu, Xuaner Chen, Rong-Hua Li·Indexed by this site · 13 hr ago· Originally publishedDefenses· Its place in the scan record →
AI summary

TRACE-MAS is a fine-grained framework for diagnosing and repairing collaboration failures in LLM multi-agent systems. It learns normal collaboration patterns from benign trajectories, detects deviations in agent state changes, message passing, and task dependency evolution, locates the responsible component through source-aware attribution, and restores collaboration with minimal intervention. On five MAS benchmarks, root-cause localization accuracy improves by 60.2%, and task recovery is consistently better than strong MAS defenses and guardrails.

Read originalarxiv.org