ag2ai/Agents_Failure_Attribution

Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

48
/ 100
Emerging

This project helps developers of multi-agent systems quickly pinpoint why their AI agents fail. You input a log of a failed multi-agent task, and it identifies which specific agent and step caused the failure, along with a natural language explanation. This is primarily for AI system developers, researchers, and engineers working with large language model-based multi-agent architectures.

349 stars.

Use this if you are building or debugging complex multi-agent AI systems and need to automate the process of identifying the root cause of task failures.

Not ideal if you are not working with multi-agent systems or primarily debugging single-agent AI models, as this tool is specifically designed for inter-agent failure attribution.

multi-agent-systems LLM-development AI-debugging agentic-workflow AI-system-engineering
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

349

Forks

23

Language

Python

License

MIT

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/ag2ai/Agents_Failure_Attribution"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.