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

2026-08-22 · Yaokun Liu, Yifan Liu, Daniel Yue Zhang, Ruichen Yao, Zelin Li, Dong Wang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2608.22130

Code (0)

등록된 구현이 없습니다.

Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates

2026-02-24 · Haoze Song, Zhihao Li, Mengyi Deng, Xin Li 외 arxiv

Neural operators (NOs) provide fast, resolution-invariant surrogates for mapping input fields to PDE solution fields, but their predictions can exhibit significant epistemic uncertainty due to finite data, imperfect opti…

Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation

2023-03-25 · Sanbao Su, Songyang Han, Yiming Li, Zhili Zhang 외

Object detection and multiple object tracking (MOT) are essential components of self-driving systems. Accurate detection and uncertainty quantification are both critical for onboard modules, such as perception, predictio…

Autonomous Vehicles Conformal Prediction motion prediction Multi-Object Tracking+6

Uncertainty Propagation Networks for Neural Ordinary Differential Equations

2025-08-22 · Hadi Jahanshahi, Zheng H. Zhu arxiv

This paper introduces Uncertainty Propagation Network (UPN), a novel family of neural differential equations that naturally incorporate uncertainty quantification into continuous-time modeling. Unlike existing neural ODE…

Trajectory Prediction

Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning

2025-06-01 · Peijin Guo, Minghui Li, Hewen Pan, Bowen Chen 외

Accurate prediction of molecular metabolic stability (MS) is critical for drug research and development but remains challenging due to the complex interplay of molecular interactions. Despite recent advances in graph neu…

Contrastive Learning Prediction Uncertainty Quantification

UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development

2026-07-02 · Temitayo Olamilekan Ogunsusi, Lijun Qian, Xishuang Dong arxiv

Software development is a complex task that demands cooperation among agents with diverse roles. Large language models (LLMs) have enabled autonomous multi-agent software development frameworks that leverage role-based c…