Metraipolis › archive › dc_ada5e06ffb0a

Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents — arXiv:2609.00065

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00065
License (as archived)
CC0-1.0
Archived
2026-10-17T06:32:41.084Z
SHA-256 of the archived text
631199272caebdcb66d1ac9bc4bb219b4497dd710fd48747e2cfdd27d9b7b5f6
Stable URL of this page
https://metraipolis.com/documento/dc_ada5e06ffb0a

How to cite

Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents — arXiv:2609.00065 — arXiv (en), https://arxiv.org/abs/2609.00065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ada5e06ffb0a (Metraipolis archive dc_ada5e06ffb0a, sha256 631199272caebdcb66d1ac9bc4bb219b4497dd710fd48747e2cfdd27d9b7b5f6)
BibTeX
@misc{dcada5e06ffb0a,
  title = {Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents — arXiv:2609.00065},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00065},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ada5e06ffb0a; sha256 631199272caebdcb66d1ac9bc4bb219b4497dd710fd48747e2cfdd27d9b7b5f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A language-model agent asked to analyse an experiment will usually return working code. Whether the analysis is defensible is a different question. A defensible analysis depends on procedural choices: which test the field accepts, which identifier namespace is authoritative, and which caveats must accompany a result. We present Scientific Agent Skills, an open library of 163 such procedures in 16 areas of practice, including genomics, cheminformatics, medical imaging, study design and scientific communication. Each skill is a directory built around a versioned, human-readable instruction file. An agent loads the file only when a task calls for it; the directory often also contains reference material and runnable scripts. We report no task-level evaluation and no host selection rate. We measure two properties of the documentation corpus: the always-resident descriptions of all 163 skills cost 7.1% of a 200,000-token window, and the median documented workflow fits within 23.9% of it, although 29 of 46 would overflow if every reference file were loaded. Openly licensed and available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.00065 — 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 2026-10-17T06:15:12.729Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).