Metraipolis › archive › dc_09f04465885c

AI-Research Agents in the Wild. From GitHub and arXiv to Regularities and Gaps — arXiv:2609.11975

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11975
License (as archived)
CC0-1.0
Archived
2026-10-16T03:11:41.369Z
SHA-256 of the archived text
eeb91cb95b7e4000e1ba0d27fa95ed90b78c614f80aba4236edee372c2cd7dea
Stable URL of this page
https://metraipolis.com/documento/dc_09f04465885c

How to cite

AI-Research Agents in the Wild. From GitHub and arXiv to Regularities and Gaps — arXiv:2609.11975 — arXiv (en), https://arxiv.org/abs/2609.11975 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09f04465885c (Metraipolis archive dc_09f04465885c, sha256 eeb91cb95b7e4000e1ba0d27fa95ed90b78c614f80aba4236edee372c2cd7dea)
BibTeX
@misc{dc09f04465885c,
  title = {AI-Research Agents in the Wild. From GitHub and arXiv to Regularities and Gaps — arXiv:2609.11975},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11975},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09f04465885c; sha256 eeb91cb95b7e4000e1ba0d27fa95ed90b78c614f80aba4236edee372c2cd7dea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11975. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI-research agents, or autoresearch systems, combine language models with tools, search, evaluation, and iterative modification of research artifacts. Their public software ecology is hard to compare because repositories, papers, benchmarks, libraries, and companion artifacts are often counted as one population. We connect two agent-drafted, human-adjudicated registries frozen on 10 June 2026: 139 canonical public repositories and 101 papers on AI-assisted research systems, each record carrying an evidence card anchored to its primary sources. Nine promoted design lineages contain 59 memberships among 52 repositories, seven of them assigned to two lineages. Against this evidence we examine six time-stamped candidate design regularities. A prospective audit of 25 newly ingested repositories observed zero of six specified trigger events, supplying bounded support for R1-R4; broader corpus evidence narrowed the original scope of R5, and a failed directional prediction leaves R6 exploratory. The paper-repository graph contains 212 curator-assigned relatedness edges: 64 of 101 papers carry at least one edge, the edges reach 23 of 139 repositories, and the six most-linked repositories carry 120 of the 212 edges (56.6%). A full-text check of seven papers shows the relation measures our curation, not the papers' citation behavior. An identity audit adjudicated against commit histories and public contributor records confirms at least 18 paper authors who also author a canonical registry repository (20 of 63 candidate author slots in 13 of 101 papers); a byline-matched tier reaches 58 identities but is reported separately and more weakly. The study contributes a source-grounded theory under prospective test, a curator-assigned map of paper-repository relatedness, and explicit limits on claims about public visibility and community structure.

Tema degli esploratori: ricerca e scienza aperta (retro-catalogo arXiv: annunci del 2026-09-14 in cs.DL).
Categorie arXiv: Digital Libraries (cs.DL).
Pagina del lavoro: https://arxiv.org/abs/2609.11975 — 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 2026-10-16T03:04:37.204Z dalla pagina https://arxiv.org/catchup/cs.DL/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).