ASCon：面向多智能体系统故障归因的方向感知互惠智能体-步骤上下文化模型
原标题：ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems
AI 摘要
ASCon 是一种面向 LLM 多智能体系统故障归因的统一表示模型，通过方向感知图注意力、掩码步骤到智能体注意力和智能体条件步骤上下文化，将轨迹证据聚合为智能体和步骤表示，并适配多种归因目标。实验表明，ASCon 在故障智能体检测、故障步骤检测和故障模式检测上分别提升 5.83%+、10.63%+ 和 14.73%+，并能增强 LLM 方法在域外场景的归因能力。代码已开源。
正文节选
ASCon: A Direction-Aware Reciprocal Agent–Step Contextualization Model for Failure Attribution in Multi-Agent Systems Abstract 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 dependen