Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
For enterprise RAG applications, this work introduces a navigation-based paradigm that outperforms existing retrieval methods, but the approach is domain-specific and incremental.
Corpus2Skill distills a document corpus into a hierarchical skill directory, enabling an LLM agent to navigate rather than retrieve, achieving state-of-the-art performance on the WixQA enterprise RAG benchmark across all quality metrics.
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.