Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems

Key points

• LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources.1
• In this work, the attribution target is the decisive error, defined as the agent--step pair whose correction would recover the failed execution.1
• Existing approaches largely identify suspicious steps without explicitly modeling how errors propagate across interactions or persist in unresolved loops, making decisive errors difficult to distinguish from downstream failure symptoms.1
• EMFA constructs a structured representation of the failed trajectory, models both cascading propagation and persistent interaction loops, and uses propagation-aware candidate screening followed by counterfactual verification to identify the decisive agent--step pair.1

Sources (1)

• [1]Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 09:44 AM

  We propose Error-Propagation Modeling for Failure Attribution (EMFA).

  LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources.

Extractive summary: sentences quoted from the sources.