# 无需检索，只需导航：将企业知识蒸馏为可导航的 Agent 技能用于 QA 和 RAG

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-16 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmo2qdhkg03rcslba2zk91nbg
- 原文链接：https://arxiv.org/abs/2604.14572

## AI 摘要

Corpus2Skill 通过迭代聚类与分层摘要生成，将企业文档语料库离线蒸馏为树状可导航技能目录，使 LLM 智能体在 serving 时能够全局浏览语料结构、主动深入主题分支并回溯优化检索路径，实现从被动消费证据到主动导航探索的范式转变。在 WixQA 企业客服基准测试中，该系统在所有质量指标上均超越密集检索、RAPTOR 及 agentic RAG 基线。

## 正文

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.