Metraipolis › archive › dc_78471c381007

Does Recursive Knowledge Construction Help Agents Verify Consensus Claims in Science? — arXiv:2610.40906

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40906
License (as archived)
CC0-1.0
Archived
2026-11-03T07:50:23.745Z
SHA-256 of the archived text
339598d15e91e25cab263b66ea9c4b08be791a1f2e1891fb54c347e8e80d4e19
Stable URL of this page
https://metraipolis.com/documento/dc_78471c381007

How to cite

Does Recursive Knowledge Construction Help Agents Verify Consensus Claims in Science? — arXiv:2610.40906 — arXiv (en), https://arxiv.org/abs/2610.40906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_78471c381007 (Metraipolis archive dc_78471c381007, sha256 339598d15e91e25cab263b66ea9c4b08be791a1f2e1891fb54c347e8e80d4e19)
BibTeX
@misc{dc78471c381007,
  title = {Does Recursive Knowledge Construction Help Agents Verify Consensus Claims in Science? — arXiv:2610.40906},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40906},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_78471c381007; sha256 339598d15e91e25cab263b66ea9c4b08be791a1f2e1891fb54c347e8e80d4e19},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent scientific agents build knowledge recursively by retrieving evidence, constructing an intermediate state, and judging whether that state contains sufficient information. These agents are evaluated end-to-end, usually without ground truth, so the effect of each design choice is unknown. Here, we examined two design axes: (1) what the recursion builds (the state of evidence) and (2) what controls it (the judge that decides when to stop). To measure them, we defined consensus scientific claim verification and measured these effects on this task, where a system must establish a claim's consensus stance from the open literature. We built a new consensus claim dataset, ProClaim-eval, including 718 claims with SUPPORT and REFUTE gold labels from five expert-curated databases spanning molecular biology, nuclear physics, and astronomy. Our instrument, ProClaim, persists an evidence state outside the model's context, so each axis can be studied with the other held fixed. Against verification systems and general-purpose agent harnesses, ProClaim ranks among the top three, with a significant advantage over the harnesses. We found that the evidence state improves performance over in-context accumulation, and it also matters what is stored in it. In addition, a trained judge that reads the evidence state performs better than fixed-round stopping. A judge trained separately and never exposed to ProClaim-eval achieves the highest agreement with the gold labels on three of five subsets, where it matches the off-the-shelf Claude Sonnet~4.6 judge and outperforms Claude Haiku~4.5. Our results support recursively maintaining a structured evidence state outside the model's context as an effective design for verifying claims in scientific agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.40906 — 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 2026-11-03T07:49:31.012Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).