Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems

arXiv:2608.29646v1 Announce Type: new Abstract: Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurate failure attribution is therefore critical for improving agent reliability. Existing topology- and spectrum-based methods exploit trajectory structures but often overlook fine-grained semantics, while LLM-based attribution methods capture semantic cues but suffer from long-context degradation over lengthy trajectories. To address these challenges, we propose DUOTRACE, a plug-and-play detection filter for LLM-based failure attribution. DUOTRACE follows a detect-before-attribute paradigm: it first detects anomalous executions and then supplies focused trajectory evidence to downstream LLM-based attribution methods. For effective VAE-based anomaly detection on agent trajectories, DUOTRACE integrates dual-view semantic-structural node representations, a Tree-LSTM-based trajectory encoder, and prefix-chain- and LLM-based data augmentation to handle heterogeneous nodes, hierarchical execution structures, and limited failure data. Experiments with six LLM-based attribution baselines show that DUOTRACE improves agent-level and step-level attribution accuracy by 8.7% and 7.0%, respectively.

Related

• Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
• Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
• CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
• REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
• Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

Source: arXiv cs.AI | 2026-09-01