相关性的新作用：在智能搜索中指导语料库交互
A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
浏览论文内容
中文总结 AI 辅助
研究提出相关性在智能搜索中作用新观点，介绍相关性感知的RipGrep搜索代理RARG，它能将相关性转化为语料库交互执行先验，提供从粗到细的相关性指导，在浏览问答和检索中提升准确性与效率，实现更快更可靠的搜索收敛。
中文摘要 AI 辅助
相关性是对文档或摘录是否包含有用证据的与查询相关的估计。现有检索代理使用相关性来选择前k个内容，但仅文档相关性无法定位、组合或验证复杂问题所需的证据。直接语料库交互（DCI）通过类似grep的探索实现了这种细粒度操作，但其与相关性无关的搜索可能会很晚才揭示有用线索并延迟收敛。最近的进展利用相关性将语料库缩小到一个交互工作空间。然而，一旦交互开始，相关性仍然不能直接指导grep首先搜索哪些文档，也不能从大量匹配中区分出信息丰富的摘录以便让语言模型首先看到。我们引入了相关性感知的RipGrep搜索代理（RARG），它将相关性转化为语料库交互的执行先验。RARG提供从粗到细的相关性指导：它对文档进行排序以便按顺序进行“ripgrep”遍历，更早地揭示全局相关线索，用与查询相关的段落初始化有希望的入口点，并对grep匹配进行重新排序以突出文档级排名可能会掩盖的信息丰富的摘录。在具有挑战性的浏览问答和推理密集型检索中，RARG在基于检索和直接交互的代理上改进了准确性 - 效率前沿。这些结果表明相关性感知交互能够实现更快、更可靠的搜索收敛。
英文摘要
Relevance is a query-dependent estimate of whether a document or excerpt contains useful evidence. Existing retrieval agents use relevance to select top-$k$ content, but document relevance alone cannot localize, compose, or verify the evidence required by complex questions. Direct Corpus Interaction (DCI) enables such fine-grained operations through grep-style exploration, but its relevance-agnostic search can expose useful clues late and delay convergence. Recent advances use relevance to narrow the corpus into a working space for interaction. Once interaction begins, however, relevance still does not directly guide which documents grep searches first or distinguish informative excerpts from a broad set of matches to let LLMs see them first. We introduce the Relevance-Aware RipGrep Search Agent (RARG), which turns relevance into an execution prior for corpus interaction. RARG provides coarse-to-fine relevance guidance: it orders documents for sequential 'ripgrep' traversal to expose globally relevant clues earlier, initializes promising entry points with query-relevant paragraphs, and reranks grep matches to surface informative excerpts that document-level ranking may otherwise obscure. Across challenging browse question answering and reasoning-intensive retrieval, RARG improves the accuracy--efficiency frontier over retrieval-based and direct-interaction agents. These results demonstrate that relevance-aware interaction enables faster and more reliable search convergence.
发表机构
- Tencent（腾讯）
- IIE-CAS（中国科学院计算技术研究所）
机构由 AI 辅助整理，请以论文原文为准。
