Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
This addresses the labor-intensive debugging of LLM multi-agent systems, though it is incremental as it formulates a new area and provides initial benchmarks.
The paper tackles the problem of automated failure attribution in LLM multi-agent systems by introducing the Who&When dataset and evaluating three methods, with the best achieving 53.5% accuracy for identifying failure-responsible agents but only 14.2% for pinpointing failure steps.
Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate a new research area: automated failure attribution for LLM multi-agent systems. To support this initiative, we introduce the Who&When dataset, comprising extensive failure logs from 127 LLM multi-agent systems with fine-grained annotations linking failures to specific agents and decisive error steps. Using the Who&When, we develop and evaluate three automated failure attribution methods, summarizing their corresponding pros and cons. The best method achieves 53.5% accuracy in identifying failure-responsible agents but only 14.2% in pinpointing failure steps, with some methods performing below random. Even SOTA reasoning models, such as OpenAI o1 and DeepSeek R1, fail to achieve practical usability. These results highlight the task's complexity and the need for further research in this area. Code and dataset are available at https://github.com/mingyin1/Agents_Failure_Attribution