{"ID":5937843,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T00:51:22.794632408Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04576","arxiv_id":"2607.04576","title":"Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation","abstract":"LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact catalog plus a one-line summary per page so the agent loads only what it needs, should make this cheaper than consulting a large monolithic index. We test that on a real 709-page markdown wiki maintained by an LLM. We retrofit it for progressive disclosure and run a preregistered ablation in which four versions of the corpus differ only in how the agent reaches the content: page bodies are byte-identical across arms, frozen as immutable git tags, so any measured difference is due to access structure alone. We cross the arms with three access conditions (a protocol-constrained agent, a free self-routing agent, and a catalog-preload regime) and grade answers blind against verified gold references with a cross-family judge. A pilot upended the premise: a capable tool-using agent never loads the index, inferring a page's path from the question and reading it directly, so the specific saving the retrofit targets does not materialize. We therefore made answer quality primary and cost secondary. Quality is non-inferior (the retrieval arm matches the index baseline within the preregistered margin) while cost falls in every regime, from about a third for a self-routing agent to well over half under catalog-preload, all confidence intervals excluding zero. The saving comes not from avoiding the index load but from more targeted access: the retrieval arm cites fewer pages and takes fewer tool turns. The study doubles as a case study in evaluation validity, applying threat-to-validity discipline to the tooling that produced it.","short_abstract":"LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact catalog plus a one-line summary per page so the agent loads only what it needs, should make this cheaper than consulting a large monolithic index. We test that on a real 7...","url_abs":"https://arxiv.org/abs/2607.04576","url_pdf":"https://arxiv.org/pdf/2607.04576v1","authors":"[\"Theodore O. Cochran\"]","published":"2026-07-06T01:03:27Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.CY\",\"cs.IR\"]","methods":"[\"Large Language Model\"]","has_code":false}