Metraipolis › archive › dc_233efa2e6b13

VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus — arXiv:2608.10665

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10665
License (as archived)
CC0-1.0
Archived
2026-10-19T06:08:32.473Z
SHA-256 of the archived text
4c78f1869aa3d2525294e005b7d101b9cabda596dec9b91288b511bbca8d54ee
Stable URL of this page
https://metraipolis.com/documento/dc_233efa2e6b13

How to cite

VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus — arXiv:2608.10665 — arXiv (en), https://arxiv.org/abs/2608.10665 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_233efa2e6b13 (Metraipolis archive dc_233efa2e6b13, sha256 4c78f1869aa3d2525294e005b7d101b9cabda596dec9b91288b511bbca8d54ee)
BibTeX
@misc{dc233efa2e6b13,
  title = {VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus — arXiv:2608.10665},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10665},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_233efa2e6b13; sha256 4c78f1869aa3d2525294e005b7d101b9cabda596dec9b91288b511bbca8d54ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10665. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Existing approaches either require expensive labelled supervision with inconsistent cross-task performance or aggregate scores from multiple sources by simple aggregations, missing a key insight: when these scores disagree, that disagreement itself carries important information about whether a reasoning step is truly valid or not. We formalise this as a coupled scoring problem among disparate, frozen verifiers, interpretable as a coordination game with a unique closed-form equilibrium where agreement signals valid steps while disagreement reveals instability. Towards this end, we propose a training-free domain-agnostic step-wise verification approach we call VERDICT: VERification via Disagreement-Informed Coupled Thresholding. To our knowledge, VERDICT is the first training-free verifier that makes the structure of cross-modal disagreement explicit and actionable. It computes consensus scores through a closed-form solution, enabling both disagreement-aware filtering and stability-conscious ranking of reasoning steps. Evaluated across six benchmarks, \method consistently improves over the base model by up to +5.95%, and performs competitively with domain-specific critics that demand extensive supervision, demonstrating that cross-modal agreement provides robust verification signals without task-specific adaptation and Training-Free Verification

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2608.10665 — 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 2026-10-19T05:57:28.288Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).