Agents
EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
arXiv:2609.01360v1 Announce Type: new Abstract: Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually ident
arXiv:2609.01360v1 Announce Type: new 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.
Related
- REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
- Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems
- CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
- From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
Source: arXiv cs.AI | 2026-09-02