评分 6 · 来源：cs.CL updates on arXiv.org · 发布于 2026-04-17
评分依据：Novel approach converting enterprise docs into navigable agent skills vs traditional RAG, practical for enterprise AI
arXiv:2604.14572v1 Announce Type: cross Abstract: 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.