Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dynamic integration of external knowledge. To further improve RAG's flexibility, Agentic RAG introduces autonomous agents into the workflow. However, Agentic RAG faces several challenges: (1) the success of each step depends on both high-quality planning and accurate search, (2) the lack of supervision for intermediate reasoning steps, and (3) the exponentially large candidate space for planning and searching. To address these challenges, we propose DecoupleSearch, a novel framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. Our approach constructs a reasoning tree, where each node represents planning and search steps. We leverage Monte Carlo Tree Search to assess the quality of each step. During inference, Hierarchical Beam Search iteratively refines planning and search candidates with dual value models. Extensive experiments across policy models of varying parameter sizes demonstrate the effectiveness of our method.

翻译：检索增强生成系统通过动态集成外部知识，已成为增强大型语言模型的关键方法论。为提升检索增强生成的灵活性，智能体检索增强生成将自主智能体引入工作流程。然而，智能体检索增强生成面临多重挑战：（1）每个步骤的成功既依赖高质量规划，也依赖精准搜索；（2）缺乏对中间推理步骤的监督；（3）规划与搜索的候选空间呈指数级增长。针对这些挑战，我们提出DecoupleSearch——一种利用双值模型解耦规划与搜索过程的新框架，使得规划推理与搜索验证可独立优化。该方法构建推理树，其中每个节点代表规划步骤与搜索步骤。我们采用蒙特卡洛树搜索评估各步骤质量。在推理阶段，分层束搜索通过双值模型迭代优化规划与搜索候选。跨不同参数规模策略模型的大量实验证明了该方法的有效性。