Agents Failure Attribution Benchmark
What it is
This repository provides the implementation and dataset for the ICML 2025 Spotlight paper 'Which Agent Causes Task Failures and When?'. It introduces a benchmark for automated failure attribution in LLM-based multi-agent systems, allowing users to identify the specific agent and step responsible for task failures.
The problem it solves
Manual inspection of failure logs in multi-agent systems is labor-intensive and difficult due to the complexity of interactions between agents.
What you could use it for
- Debugging complex multi-agent system failures automatically
- Evaluating the effectiveness of different failure attribution methods (e.g., step-by-step vs. all-at-once)
- Providing intermediate feedback signals for agent self-improvement or reinforcement learning
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.