arXiv AI
Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 3
Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search
arXiv:2607. 29055v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly deployed to solve complex tasks.
arXiv AI
Aug 7
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
arXiv:2608. 06346v1 Announce Type: new Abstract: LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging.
arXiv AI
Oct 15
When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems
arXiv:2610.15459v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protoc...
arXiv AI
Jul 14
AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
arXiv AI
Jul 22
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
arXiv:2607. 18754v1 Announce Type: new Abstract: LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it.
arXiv AI
Oct 1
Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.