EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems

2026-09-01

AI Summary

本文提出EDGE框架，通过构建错误依赖图并验证因果子集来解决多代理LLM系统中的多错误归因问题。

Abstract

Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually identify a responsible agent, step, or root cause, but do not explicitly model dependency between errors. We introduce EDGE, an Error Dependency Graph-guided multi-Error attribution framework. EDGE constructs an error dependency graph from observed error events and validates a reliable causal subset through counterfactual rollout. The inference graph guides a two-stage LLM-as-judge detector for error attribution, and the intervention-validated subgraph provides a more reliable basis for explanation and repair analysis. Experiments on TRAIL and MAST show that EDGE improves category-level multi-error attribution across most evaluated models and settings. Experiments with adapted Who&When-style prompts show that the graph helps across prompting strategies. These results suggest that dependency structure is a useful diagnostic prior for agent failures beyond isolated root-cause prediction.

Problem

• multi-error attribution
• error dependency
• large language model

Innovation

• Error Dependency Graph
• Multi-Error Attribution
• Counterfactual Rollout
• LLM-as-judge Detector