不檢索，導航：將企業知識提煉為可導航的智能體技能以實現問答與檢索增強生成（注：此標題採用意譯方式，將"Navigate"譯為"導航"以呼應"不檢索"的對比概念，同時將"Agent Skills"譯為"智能體技能"符合技術文獻慣例。副標題通過"實現"動詞銜接，使技術路徑與應用場景的邏輯關係更清晰。）

摘要

检索增强生成（RAG）技术虽能将大语言模型的响应植根于外部证据，却将模型视为搜索结果的被动消费者：模型无法感知语料库的组织结构及未检索内容，这限制了其回溯或整合零散证据的能力。我们提出Corpus2Skill方法，通过离线处理将文档语料库提炼为分层技能目录，使大语言模型智能体在运行时能自主导航该目录。该编译管道通过迭代式文档聚类生成各层级的LLM摘要，最终物化为可导航的技能文件树。运行时，智能体可纵览语料库全貌，借助逐级细化的摘要深入主题分支，并通过文档ID检索完整内容。由于层级结构显式可见，智能体能自主推理检索路径、回溯无效分支并实现跨分支证据整合。在企业客户支持基准测试WixQA中，Corpus2Skill在各项质量指标上均优于稠密检索、RAPTOR及智能RAG基线方法。

English

Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results: it never sees how the corpus is organized or what it has not yet retrieved, limiting its ability to backtrack or combine scattered evidence. We present Corpus2Skill, which distills a document corpus into a hierarchical skill directory offline and lets an LLM agent navigate it at serve time. The compilation pipeline iteratively clusters documents, generates LLM-written summaries at each level, and materializes the result as a tree of navigable skill files. At serve time, the agent receives a bird's-eye view of the corpus, drills into topic branches via progressively finer summaries, and retrieves full documents by ID. Because the hierarchy is explicitly visible, the agent can reason about where to look, backtrack from unproductive paths, and combine evidence across branches. On WixQA, an enterprise customer-support benchmark for RAG, Corpus2Skill outperforms dense retrieval, RAPTOR, and agentic RAG baselines across all quality metrics.

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG

摘要

Support