Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures
cs.MA, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Sources
- Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution
- AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
- Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems
- Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
- Where LLM Agents Fail and How They can Learn From Failures
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery