cs.CLNov 11, 2026

CoLFA: Collaboration-Guided Lightweight Failure Attribution for LLM-Based Multi-Agent Systems

Authors: Yufei Luo, Yuchen Ling, Chunrong Fang

Organizations: Nanjing University

Abstract

Failure attribution in multi-agent systems requires tracing error formation to identify the decisive error step and the responsible agent. However, agents' division of work and information exchange lead to Interleaved Steps and Cluttered Content, requiring models to link executions and check details in lengthy records. This makes it difficult to balance localization accuracy and token cost. We find that multi-agent collaboration also leaves records of how executions connect and content passes between them as results are formed, providing evidence for tracing error formation. Based on this observation, we propose CoLFA (Collaboration-Guided Lightweight Failure Attribution), which uses collaboration cues to organize the attribution input according to how results are formed, determining which steps are examined and how their content is presented. Through Handoff-Guided Step Expansion and Cross-Referenced Content Organization, CoLFA helps the model focus on examining error formation and the role of each decision while reducing the processing of irrelevant and repeated records. Across five settings spanning Who&When and LongRCA and three backbone models, CoLFA achieves the highest exact step-localization accuracy with the lowest token consumption. Compared with individual baselines in each setting, CoLFA improves accuracy by up to 37.50% and reduces token consumption by up to 97.6%.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems

    Oct 8, 2026Jiaqi Liao, Yuanzhao Zhai, Huanxi Liu +5Failure Attribution for LLM AgentsAgent Failure Analysis

  2. DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems

    Sep 4, 2026Zehao Wang, Lanjun Wang, Shilong Jin +2Agent Failure AnalysisMulti-Agent LLM Systems