在声明验证中协调搜索赋能的推理与推理引导的搜索
Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification
AI总结：
针对多跳声明验证中推理与搜索交织的挑战，提出层级智能体框架HARIS，通过高低层智能体分别负责推理建链和迭代搜索，用强化学习训练，在两个基准上取得优异性能。
摘要：
多跳声明验证本质上具有挑战性，需要多步推理构建验证链，同时迭代搜索信息以发现隐藏的桥接事实。这一过程从根本上是相互交织的：有效推理依赖动态检索到的证据，而有效搜索需要推理基于部分信息优化查询。为此，我们提出层级智能体推理与信息搜索框架（Hierarchical Agent Reasoning and Information Search，HARIS），显式建模推理驱动搜索与搜索赋能推理的协同过程。HARIS由一个高层推理智能体和一个低层搜索智能体组成：前者专注于构建主验证链，在需要更多信息时生成事实性问题；后者迭代检索更多信息，并基于中间发现优化搜索。该设计让每个智能体专注于各自任务，提升了验证准确性和可解释性。HARIS采用基于结果奖励的强化学习训练。在EX-FEVER和HOVER基准上的实验结果表明，HARIS取得了优异性能，极大推进了多跳声明验证的发展。
英文摘要：
Multi-hop claim verification is inherently challenging, requiring multi-step reasoning to construct verification chains while iteratively searching for information to uncover hidden bridging facts. This process is fundamentally interleaved, as effective reasoning relies on dynamically retrieved evidence, while effective search demands reasoning to refine queries based on partial information. To achieve this, we propose Hierarchical Agent Reasoning and Information Search (HARIS), explicitly modeling the coordinated process of reasoning-driven searching and search-informed reasoning. HARIS consists of a high-level reasoning agent that focuses on constructing the main verification chain, generating factual questions when more information is needed, and a low-level search agent that iteratively retrieves more information, refining its search based on intermediate findings. This design allows each agent to specialize in its respective task, enhancing verification accuracy and interpretability. HARIS is trained using reinforcement learning with outcome-based rewards. Experimental results on the EX-FEVER and HOVER benchmarks demonstrate that HARIS achieves strong performance, greatly advancing multi-hop claim verification.
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。
