返回全部动态
PropUQ-MAS：面向LLM多智能体系统的传播感知不确定性量化
原标题：PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems
AI 摘要
PropUQ-MAS 是一个面向 LLM 多智能体系统（MAS）的不确定性量化框架，通过将执行过程建模为通信图，结合局部不确定性与上游传播的不确定性，实现逐步可靠性估计。实验表明，该方法在 AUROC 和 PRR 指标上平均相对提升显著，并支持任意拓扑结构和在线监控。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems Abstract LLM-based multi-agent systems (MAS) solve complex tasks through communication among role-specialized agents. However, inter-agent dependencies introduce reliability risks beyond isolated agent failures. For instance, errors in intermediate messages could be inherited and amplified by downstream agents. Existing uncertainty quantification (UQ) methods mainly target isolated responses or single-agent reas
发布时间：2026-08-25 12:00
抓取时间：2026-08-25 12:51
来源机构：arXiv