ASCon：面向多智能体系统故障归因的方向感知互惠智能体-步骤上下文模型
ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems
浏览论文内容
中文总结 AI 辅助
该研究针对多智能体系统故障归因中不同目标间证据依赖关注不足的问题，提出ASCon模型，通过方向感知图注意力等技术聚合轨迹证据，提升了故障智能体、步骤、模式的检测性能及域外归因能力。
中文摘要 AI 辅助
基于大语言模型（LLM）的多智能体系统（MAS）中的故障归因旨在通过识别负责目标，包括故障智能体、错误步骤和故障模式，回答谁导致了故障、故障何时发生以及为何发生。现有方法主要专注于为特定归因目标开发专用模型，而对这些目标之间的证据依赖关系关注有限。尽管这些归因目标各不相同，但它们都依赖于MAS轨迹中的共同诊断证据，包括任务约束、智能体角色、行为历史和智能体间交互。这种共性促使我们开发一种统一表示模型，将轨迹证据聚合为单个智能体和步骤表示，随后可适配不同的归因目标。据此，我们提出ASCon，一种面向多个故障归因目标的方向感知互惠智能体-步骤上下文模型。ASCon引入方向感知图注意力以建模执行上下文、掩码步骤-智能体注意力以构建感知行为的智能体表示，以及智能体条件步骤上下文化以将智能体上下文重新融入步骤表示。所得的上下文化表示可通过轻量的目标特定头实现不同的归因目标。实验表明，ASCon可将故障智能体检测的微准确率提升5.83%以上，故障步骤检测的微准确率提升10.63%以上，故障模式检测的宏F1值提升14.73%以上；同时，它还能显著增强基于LLM的方法在域外场景中的归因能力。
英文摘要
Failure attribution in LLM-based multi-agent systems (MAS) aims to answer who caused failures, when they occurred, and why by identifying responsible targets including faulty agents, erroneous steps, and failure modes. Existing methods have primarily focused on developing dedicated models for specific attribution targets, with limited attention to the evidential dependencies among them. Despite these attribution targets are different, they rely on common diagnostic evidence from MAS trajectories, including task constraints, agent roles, behavioral histories and inter-agent interactions. This commonality motivates us to develop a unified representation model that aggregates the trajectory evidence into individual agent and step representations, which can subsequently be adapted to different attribution targets. Accordingly, we propose ASCon, a direction-aware reciprocal \textbf{A}gent--\textbf{S}tep \textbf{Con}textualization model for multiple failure attribution targets. ASCon introduces direction-aware graph attention to model execution context, masked step-to-agent attention to construct behavior-aware agent representations, and agent-conditioned step contextualization to incorporate agent context back into step representations. The resulting contextualized representations enable different attribution targets through lightweight target-specific heads. Experiments show that ASCon can improve faulty-agent detection by 5.83\%+ in micro-accuracy, faulty-step detection by 10.63\%+ in micro-accuracy, and failure-mode detection by 14.73\%+ in Macro-F1. Meanwhile, it can also substantially enhance the LLM-based methods' attribution capabilities in out-of-domain scenarios.
