SIRAG：基于过程监督多智能体框架实现稳定且可解释的检索增强生成
SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework
AI总结：
本文提出SIRAG框架，通过决策者与知识选择器两个轻量级智能体及过程级奖励监督和PPO训练，在无需修改检索器和生成器的前提下提升RAG的准确性、稳定性和可解释性。
摘要：
检索增强生成（RAG）使大语言模型（LLM）能够访问外部知识源，但RAG的有效性依赖于检索器与生成器之间的协调。由于这些组件是独立开发的，它们的交互往往不是最优的：检索器可能返回不相关或冗余的文档，而生成器可能未能充分利用检索到的证据。在这项工作中，我们提出了一个过程监督的多智能体框架，以弥合检索器与生成器之间的差距。该框架引入了两个轻量级智能体：一个决策者（Decision Maker），用于决定何时继续检索或停止检索以进行答案生成；以及一个知识选择器（Knowledge Selector），用于过滤检索到的文档，仅保留最有用的证据。为了提供细粒度的监督，我们采用LLM-as-a-Judge，通过过程级奖励评估每个中间动作，确保比仅依赖最终答案正确性更准确的责任分配。我们进一步采用树结构展开策略来探索多样化的推理路径，并以端到端的方式使用近端策略优化（PPO）训练两个智能体。在单跳和多跳问答基准上的实验表明，与标准RAG基线相比，我们的方法实现了更高的准确率、更稳定的收敛，并产生更具可解释性的推理轨迹。重要的是，所提出的框架是模块化和即插即用的，无需修改检索器或生成器，使其适用于现实世界中的RAG应用。
英文摘要：
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are developed independently, their interaction is often suboptimal: the retriever may return irrelevant or redundant documents, while the generator may fail to fully leverage retrieved evidence. In this work, we propose a process-supervised multi-agent framework to bridge the gap between retriever and generator. The framework introduces two lightweight agents: a Decision Maker, which determines when to continue retrieval or stop for answer generation, and a Knowledge Selector, which filters retrieved documents to retain only the most useful evidence. To provide fine-grained supervision, we employ an LLM-as-a-Judge that evaluates each intermediate action with process-level rewards, ensuring more accurate credit assignment than relying solely on final answer correctness. We further adopt a tree-structured rollout strategy to explore diverse reasoning paths, and train both agents with Proximal Policy Optimization (PPO) in an end-to-end manner. Experiments on single-hop and multi-hop question answering benchmarks show that our approach achieves higher accuracy, more stable convergence, and produces more interpretable reasoning trajectories compared with standard RAG baselines. Importantly, the proposed framework is modular and plug-and-play, requiring no modification to the retriever or generator, making it practical for real-world RAG applications.
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。
