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

2026-08-30

AI Summary

为解决多智能体系统中执行失败归因问题，提出DUOTRACE方法，先检测异常执行再提供聚焦轨迹证据给归因模型，提高了归因准确性。

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.

Problem

• failure attribution
• multi-agent systems
• large language model

Innovation

• DUOTRACE
• detect-before-attribute
• VAE-based anomaly detection
• dual-view semantic-structural node representations
• Tree-LSTM-based trajectory encoder