Metraipolis › archive › dc_feb68fb980eb

Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents — arXiv:2609.25991

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.25991
License (as archived): CC0-1.0
Archived: 2026-10-08T16:38:56.428Z
SHA-256 of the archived text: 677d16b7583b2a53b9729b90ba64c963185b7e8bd04cc6910481022da5785ed3
Stable URL of this page: https://metraipolis.com/documento/dc_feb68fb980eb

How to cite

Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents — arXiv:2609.25991 — arXiv (en), https://arxiv.org/abs/2609.25991 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_feb68fb980eb (Metraipolis archive dc_feb68fb980eb, sha256 677d16b7583b2a53b9729b90ba64c963185b7e8bd04cc6910481022da5785ed3)

BibTeX

@misc{dcfeb68fb980eb,
  title = {Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents — arXiv:2609.25991},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25991},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_feb68fb980eb; sha256 677d16b7583b2a53b9729b90ba64c963185b7e8bd04cc6910481022da5785ed3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25991. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 Knowledge-as-Skill, an organization scheme that makes a knowledge base discoverable, navigable, and self-descriptive. It has three layers: a discovery layer centered on this http URL ; a navigation layer with one this http URL per directory; and a knowledge layer containing documents with YAML frontmatter for topic, type, provenance, and lifecycle. The design follows the Open Knowledge Format (OKF) and the Skill protocol without modifying the agent framework. We also provide knowledge-as-skill, a pipeline for converting heterogeneous collections of PDFs, Word files, web exports, and notes into this structure. In a preliminary evaluation on the WixQA enterprise customer-support benchmark, our setup obtains 0.889 Factuality and 0.816 Context Recall, compared with reported Corpus2Skill values of 0.767 and 0.708. It obtains slightly lower Faithfulness, lower Context Precision, and more interaction turns. Because the models, prompts, and knowledge-package construction differ, these results are directional cross-work evidence rather than a controlled comparison.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.25991 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T15:55:51.487Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).