面向智能体RAG管道的贝叶斯不确定性传播：多跳问答的概念验证研究
Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering
AI总结：
提出一种不确定性感知的智能体RAG框架，通过贝叶斯网络传播各阶段的不确定性信号，以估计系统级不确定性并定位潜在故障点，在HotpotQA上表现有效，但在StrategyQA上受限于校准问题。
摘要：
可信赖地部署智能体检索增强生成（RAG）系统需要机制来估计多阶段推理管道何时可能失败。本文提出一个不确定性感知的智能体检索增强生成（RAG）框架，其中规划器、评估器和生成器阶段产生源自语义发散和生成器自评估的不确定性信号。这些信号通过贝叶斯网络（BN）传播，以估计系统级不确定性，并提供跨工作流潜在故障点的节点级指标。该方法在StrategyQA和HotpotQA上使用GPT-3.5-Turbo和GPT-4.1-Nano进行评估，采用接收者操作特征曲线下面积（AUROC）、准确率-拒绝曲线下面积（AUARC）、期望校准误差（ECE）和Brier分数来评估区分能力、选择性预测和校准。结果表明，贝叶斯传播在HotpotQA上更有效，其中不确定性在多跳推理阶段累积，而StrategyQA暴露了由校准不良和不可靠的上游信号引起的局限性。本研究将贝叶斯不确定性传播定位为一种有前景但初步的智能体RAG系统监控机制，未来需要在工业领域（如海上风电（OSW）维护决策支持）进行验证。
英文摘要：
Trustworthy deployment of Agentic Retrieval-Augmented Generation (RAG) systems requires mechanisms for estimating when multi-stage reasoning pipelines may fail. This paper presents an uncertainty-aware Agentic Retrieval-Augmented Generation (RAG) framework in which planner, evaluator and generator stages produce uncertainty signals derived from semantic divergence and generator self-evaluation. These signals are propagated through a Bayesian Network (BN) to estimate system-level uncertainty and provide node-level indicators of potential failure points across the workflow. The approach is evaluated on StrategyQA and HotpotQA using GPT-3.5-Turbo and GPT-4.1-Nano, with Area Under the Receiver Operating Characteristic Curve (AUROC), Area Under the Accuracy-Rejection Curve (AUARC), Expected Calibration Error (ECE), and Brier Score used to assess discrimination, selective prediction and calibration. Results show that Bayesian propagation is more effective on HotpotQA, where uncertainty accumulates across multi-hop reasoning stages, while StrategyQA exposes limitations caused by miscalibration and unreliable upstream signals. The study positions Bayesian uncertainty propagation as a promising but preliminary mechanism for monitoring Agentic RAG systems, with future validation required in industrial domains such as Offshore Wind (OSW) maintenance decision support.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
