PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems

2026-08-22

AI Summary

为解决多智能体系统中不确定性传播问题，提出PropUQ-MAS框架，通过构建通信结构图并结合局部与上游不确定性来估计每步的可靠性。

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 reasoning, and therefore fail to capture uncertainty propagation in MAS. To this end, we propose PropUQ-MAS, an error propagation-aware UQ framework that represents MAS execution as a communication-structured graph and estimates each step's reliability by combining local uncertainty with uncertainty inherited from upstream messages. Extensive experiments demonstrate that PropUQ-MAS consistently improves UQ in MAS, with average relative gains of +6.10% in AUROC and +47.58% in PRR.

Problem

• LLM-based multi-agent systems
• uncertainty quantification
• inter-agent dependencies
• error propagation
• reliability risks

Innovation

• Propagation-Aware
• Uncertainty Quantification
• LLM Multi-Agent Systems
• Communication-Structured Graph