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.
DCFA is proposed, a training-free framework for failure attribution that integrates a global module that constructs structured causal-inspired dependency graphs from system traces to identify the initial decisive error, and a local module that applies local counterfactual-inspired reasoning to refine causal-inspired at...
Ze-Hao Wang, Lanjun Wang, Shi-Long Jin et al.· 1 citation
ASCon is proposed, a direction-aware reciprocal \textbf{A}gent--\textbf{S}tep \textbf{Con}textualization model for multiple failure attribution targets that introduces direction-aware graph attention to model execution context, masked step-to-agent attention to construct behavior-aware agent representations, and agent-...
Shu-Yu Jiang, Yue Ran, Kaiyu Xu et al.· 0 citations
Adaptive Influence Graphs is introduced, a two-stage agentic framework that first transforms a failed trace into a structured graph and then navigates it to identify the critical error and establishes a new state of the art on Who&When, the standard benchmark for multi-agent failure attribution.
Yarden Bakish, Amir Dudai, Roy Ganz et al.· 1 citation
The generalizability of the diagnose-then-correct paradigm is established and it is demonstrated that in low-resource settings, focusing reflection on reasoning steps after the decisive error step achieves comparable quality to reflecting on the complete failure trajectory.
Xiao-Qing Wang, Ke-Man Huang, Bin Liang et al.· 0 citations
Errors in LLM agent executions and their visible consequences can be separated by many steps, making decisive-error localization a matter of understanding both step content and step dependencies. We introduce DeFA, a dependency-guided framework for agent failure attribution. DeFA first combines protocol relations and s...
Bo Deng, Xin-Lei Zheng, Yi-Xun Wei et al.· 1 citation· ⚡1
DUOTRACE follows a detect-before-attribute paradigm: it first detects anomalous executions and then supplies focused trajectory evidence to downstream LLM-based attribution methods, which improves agent-level and step-level attribution accuracy.
Jia-Yi Zhang, Ze-Xin Wang, DecisionMakingRon Sun et al.· 1 citation
