Metraipolis › archive › dc_573b505af4fa

When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning — arXiv:2610.04686

Source
arXiv
Original
https://arxiv.org/abs/2610.04686
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:00.653Z
SHA-256 of the archived text
34353149353cb8b4ce49d750c0e1239ba750252b1a606387f603f21fb4051f68
Stable URL of this page
https://metraipolis.com/documento/dc_573b505af4fa

How to cite

When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning — arXiv:2610.04686 — arXiv, https://arxiv.org/abs/2610.04686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_573b505af4fa (Metraipolis archive dc_573b505af4fa, sha256 34353149353cb8b4ce49d750c0e1239ba750252b1a606387f603f21fb4051f68)
BibTeX
@misc{dc573b505af4fa,
  title = {When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning — arXiv:2610.04686},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04686},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_573b505af4fa; sha256 34353149353cb8b4ce49d750c0e1239ba750252b1a606387f603f21fb4051f68},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent debate can improve reasoning, yet often fails to beat simple majority voting. We argue that successful debate requires two distinct mechanisms: proposal supply must surface a correct answer, and readout must identify that answer when voting misses it. We formalize the first requirement through recoverable headroom, which measures cases where a correct proposal is available but the majority answer is wrong. For the second, we develop Latent Verification Debate (LVD), an accounting model in which candidate proposals receive answer-specific verification evidence before final generation. Controlled fixed-proposal interventions estimate this latent effect in equivalent peer-support units and show that correct evidence changes answer probabilities and generated decisions while proposal supply remains fixed. To improve proposal supply, we construct societies from neural-thicket agents using labeled and label-free coverage objectives. Across two backbones and matched-budget reasoning benchmarks, coverage-selected societies increase complementary proposal supply and improve aggregate accuracy in repeated stochastic evaluations. Round-level controls further show that interaction provides gains beyond applying the same finalizer directly to the initial proposals. These results identify proposal coverage and truth-sensitive evidence use as complementary conditions for debate to outperform voting. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2610.04686 — 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 2026-10-06T05:23:50.228Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).