Metraipolis › archive › dc_0f0cfeded08a

Does Reasoning Make Language Models Agree? — arXiv:2610.41691

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41691
License (as archived): CC0-1.0
Archived: 2026-11-03T08:05:43.715Z
SHA-256 of the archived text: 7f150d888124b459c6295d4bfebb8b32c798093c98edfbae816c4bef6527e3be
Stable URL of this page: https://metraipolis.com/documento/dc_0f0cfeded08a

How to cite

Does Reasoning Make Language Models Agree? — arXiv:2610.41691 — arXiv (en), https://arxiv.org/abs/2610.41691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f0cfeded08a (Metraipolis archive dc_0f0cfeded08a, sha256 7f150d888124b459c6295d4bfebb8b32c798093c98edfbae816c4bef6527e3be)

BibTeX

@misc{dc0f0cfeded08a,
  title = {Does Reasoning Make Language Models Agree? — arXiv:2610.41691},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41691},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f0cfeded08a; sha256 7f150d888124b459c6295d4bfebb8b32c798093c98edfbae816c4bef6527e3be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language models face two opposing concerns: monoculture, in which models err in correlated ways, and multiplicity, in which equally accurate models make conflicting decisions. The rise of reasoning models has complicated this debate: On the one hand, reasoning may increase model agreement if models anchor on the same salient features or follow similar reasoning paths. On the other hand, stochastic reasoning traces may introduce additional branch points leading to more diverse predictions. We resolve this tension by distinguishing reasoning as an intervention from reasoning as an observed behavior. We compare agreement under controlled changes in reasoning effort with agreement across observed reasoning lengths, measuring both against the agreement expected from model accuracy. Across nine models from two developers and three classification tasks, enabling reasoning increases agreement between models evaluated on the same individuals. Yet the individuals who elicit longer reasoning traces receive less consistent predictions across models. Both patterns persist after accounting for differences in accuracy. Asking models to reason more thus promotes agreement, while observing them reason longer signals disagreement.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2610.41691 — 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 2026-11-03T07:59:53.624Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).