cs.LGNov 17, 2026

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

Authors: Zekai Chen, Yihan Sun, Xunkai Li, Xun Wu, Xinmo Jin, Yinlin Zhu, Haodong Lu, Xuaner Chen, 

Organizations: Beijing Institute of Technology · Minzu University of China · Sun Yat-sen University · Shandong University, Weihai

Abstract

LLM-based multi-agent systems (MAS) rely on not only individual agent behaviors but also the interactions that connect agents, including message exchanges and task dependencies. Existing MAS safeguards mainly perform agent-level anomaly detection, which becomes insufficient when failures originate from agent interactions and detected anomalies do not necessarily reveal their true sources. To address this limitation, we propose TRACE-MAS, a finer-grained framework for diagnosing and repairing MAS failures. TRACE-MAS learns normal collaborative execution patterns from benign trajectories and detects deviations in agent state changes, message transitions, and task dependency evolutions. It further identifies responsible execution elements through source-aware attribution and selects minimal interventions to restore collaboration while preserving task-critical capabilities. Experiments on five MAS benchmarks demonstrate that TRACE-MAS significantly improves root-cause localization accuracy by 60.2% and achieves consistent gains in task recovery over strong MAS safeguards.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

    Aug 26, 2026Zhongwen Luan, Xiaoyu Zhang, Ming Hu +3LLM Agent ReliabilityAgent Failure Analysis

  2. MASTraceBench: Diagnosing Collaboration Gains through Proposal Trajectories in LLM-Based Multi-Agent Systems

    Sep 28, 2026Yapeng Li, Songze Li, Shuang Yu +4Multi-Agent LLM SystemsMulti-Agent Collaboration