HierSearch：融合本地与网络搜索的层次化企业深度搜索框架
HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches
AI总结：
针对企业需同时检索本地与网络知识源的问题，提出基于层次化强化学习的智能体深度搜索框架HierSearch，结合低层检索智能体、高层规划器与知识精炼器，有效提升了多源检索与最终回答的准确性。
摘要：
近期，大型推理模型展现了强大的数学和编程能力，而深度搜索则利用其推理能力应对具有挑战性的信息检索任务。现有的深度搜索工作通常局限于单一知识源，要么是本地，要么是网络。然而，企业通常需要能够同时在本地和网络语料库上利用搜索工具的私有深度搜索系统。使用扁平强化学习（RL）训练配备多种搜索工具的智能体是一个直接的想法，但存在训练数据效率低和对复杂工具掌握不佳等问题。为解决上述问题，我们提出了一个使用层次化RL训练的层次化智能体深度搜索框架HierSearch。在低层，训练本地深度搜索智能体和网络深度搜索智能体从其对应领域检索证据。在高层，规划智能体协调低层智能体并提供最终答案。此外，为防止直接复制答案和错误传播，我们设计了一个知识精炼器，用于过滤低层智能体返回的幻觉和不相关证据。实验表明，与扁平RL相比，HierSearch取得了更好的性能，并在涵盖通用、金融和医疗领域的六个基准测试中，优于各种深度搜索和多源检索增强生成基线。
英文摘要：
Recently, large reasoning models have demonstrated strong mathematical and coding abilities, and deep search leverages their reasoning capabilities in challenging information retrieval tasks. Existing deep search works are generally limited to a single knowledge source, either local or the Web. However, enterprises often require private deep search systems that can leverage search tools over both local and the Web corpus. Simply training an agent equipped with multiple search tools using flat reinforcement learning (RL) is a straightforward idea, but it has problems such as low training data efficiency and poor mastery of complex tools. To address the above issue, we propose a hierarchical agentic deep search framework, HierSearch, trained with hierarchical RL. At the low level, a local deep search agent and a Web deep search agent are trained to retrieve evidence from their corresponding domains. At the high level, a planner agent coordinates low-level agents and provides the final answer. Moreover, to prevent direct answer copying and error propagation, we design a knowledge refiner that filters out hallucinations and irrelevant evidence returned by low-level agents. Experiments show that HierSearch achieves better performance compared to flat RL, and outperforms various deep search and multi-source retrieval-augmented generation baselines in six benchmarks across general, finance, and medical domains.
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。
