SOURCE-LINKED INTELLIGENCE

Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hindering their real-world deployment. Existing MAS debugging and repair methods typically rely on rerunning and resampling the entire execution trajectory. However, a fundamental question remains to be answered: do these methods causally repair MAS failures or merely stochastically repair by leveraging the randomness of LLM sampling? To evaluate the effectiveness of MAS repair methods, we introduce SymTrace, a controlled ev

Read original source ↗ Open in workspace

recordType

paper

region

Global