Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents — Wu (2026)

1 More Paper · Oct 7, 2026 · 27m · transcript

Retrieval-augmented generation (RAG) gives large language models (LLMs) access to external knowledge, but its conventional retrieve-concatenate-generate pipeline makes retrieval decisions on behalf of the model. As tool use and agent loops become more reliable, an agent can decide whether to retrieve, what to inspect, and when to stop. This shift exposes a new bottleneck: the agent may not know what a knowledge base contains. Traditional knowledge bases expose documents as anonymous text chunks with limited information about scope, purpose, provenance, or relations. We propose…