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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Yiqun, Wei, Pengfei, Hsieh, Lawrence B.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918502622822400
author Sun, Yiqun
Wei, Pengfei
Hsieh, Lawrence B.
author_facet Sun, Yiqun
Wei, Pengfei
Hsieh, Lawrence B.
contents Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results, with no view of how the corpus is organized or what it has not yet seen. We present Corpus2Skill, which distills a document corpus offline into a hierarchical skill directory and lets an LLM agent navigate it at serve time, drilling from a bird's-eye view through progressively finer summaries down to documents, and backtracking when a branch is unproductive. On an enterprise customer-support benchmark, Corpus2Skill improves both answer quality and grounding over single-shot dense, hybrid, hierarchical-retrieval, and agentic RAG baselines at a moderate cost tradeoff. A ten-subset generalization study further shows that corpus navigation is not a universal replacement for retrieval: it consistently helps on single-domain corpora with a recoverable topical taxonomy, but flat retrieval remains preferable on open-domain factoid pools or homogeneous-tabular corpora that defeat top-level clustering. We characterize this scope distinction and discuss it as a design guideline for knowledge-grounded systems. Code is available at https://github.com/dukesun99/Corpus2Skill.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14572
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
Sun, Yiqun
Wei, Pengfei
Hsieh, Lawrence B.
Information Retrieval
Artificial Intelligence
Computation and Language
Multiagent Systems
Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results, with no view of how the corpus is organized or what it has not yet seen. We present Corpus2Skill, which distills a document corpus offline into a hierarchical skill directory and lets an LLM agent navigate it at serve time, drilling from a bird's-eye view through progressively finer summaries down to documents, and backtracking when a branch is unproductive. On an enterprise customer-support benchmark, Corpus2Skill improves both answer quality and grounding over single-shot dense, hybrid, hierarchical-retrieval, and agentic RAG baselines at a moderate cost tradeoff. A ten-subset generalization study further shows that corpus navigation is not a universal replacement for retrieval: it consistently helps on single-domain corpora with a recoverable topical taxonomy, but flat retrieval remains preferable on open-domain factoid pools or homogeneous-tabular corpora that defeat top-level clustering. We characterize this scope distinction and discuss it as a design guideline for knowledge-grounded systems. Code is available at https://github.com/dukesun99/Corpus2Skill.
title Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
topic Information Retrieval
Artificial Intelligence
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2604.14572