Metraipolis › archive › dc_b44c19b365db

Operon-S1: a fast decision controller for long-horizon biomedical agents — arXiv:2610.41350

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41350
License (as archived): CC0-1.0
Archived: 2026-11-02T04:43:26.157Z
SHA-256 of the archived text: 23e14c3a57031dbba78f65e3cde24854695e7f30ae570b3657483eaa725d1c57
Stable URL of this page: https://metraipolis.com/documento/dc_b44c19b365db

How to cite

Operon-S1: a fast decision controller for long-horizon biomedical agents — arXiv:2610.41350 — arXiv (en), https://arxiv.org/abs/2610.41350 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b44c19b365db (Metraipolis archive dc_b44c19b365db, sha256 23e14c3a57031dbba78f65e3cde24854695e7f30ae570b3657483eaa725d1c57)

BibTeX

@misc{dcb44c19b365db,
  title = {Operon-S1: a fast decision controller for long-horizon biomedical agents — arXiv:2610.41350},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41350},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b44c19b365db; sha256 23e14c3a57031dbba78f65e3cde24854695e7f30ae570b3657483eaa725d1c57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41350. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language-model agents now carry out long scientific work in biology, but their judgements about conventions, skills, errors, evidence and stopping are made inside the reasoning that does the work, where they cannot be measured, replaced or improved on their own. Here we present Operon-S1, a fast decision system, a System 1 for the agent, that separates judging from doing. A decision harness poses the agent's recurring judgements as closed questions at 13 decision points and acts only through fixed messages that never contain an answer, so any model that answers the questions can serve as the judge. Across seven life-science benchmarks, a local decision model took over these judgements in 0.6 s at the median for an in-loop request on CPU at no request cost, with no measurable change in the agent's score on five of six benchmarks, whereas the general language model that drives the agent, asked the same questions, accounted for 8.0% to 35.2% of task cost. Every decision is recorded with its consequence. Retraining on labels from task construction, verifiers or execution raised decision accuracy on every question in each of three trained versions, and a new version enters service only through a promotion gate. Task-level results in this study use the public checkpoint. The same closed decisions serve wet-laboratory protocol troubleshooting and the design of a germline target enrichment panel. Like the regulator of an operon, which switches genes on and off without making their products, Operon-S1 steers the agent without doing its work, and makes the agent's judgements a layer that can be measured, replaced and trained.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41350 — 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 2026-11-02T04:42:12.366Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).