Metraipolis › archive › dc_feea0d316784

Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries — arXiv:2610.02005

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02005
License (as archived)
CC0-1.0
Archived
2026-10-06T12:06:42.810Z
SHA-256 of the archived text
e70dec3ee82826d6f4fec681296190cb1f59cd1c22d7930c57256c63cb38b672
Stable URL of this page
https://metraipolis.com/documento/dc_feea0d316784

How to cite

Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries — arXiv:2610.02005 — arXiv (en), https://arxiv.org/abs/2610.02005 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_feea0d316784 (Metraipolis archive dc_feea0d316784, sha256 e70dec3ee82826d6f4fec681296190cb1f59cd1c22d7930c57256c63cb38b672)
BibTeX
@misc{dcfeea0d316784,
  title = {Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries — arXiv:2610.02005},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02005},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_feea0d316784; sha256 e70dec3ee82826d6f4fec681296190cb1f59cd1c22d7930c57256c63cb38b672},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02005. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A multi-LLM \emph{council} lets several large language models (LLMs) deliberate on a question and return an answer together with a confidence estimate. As these systems become increasingly used for reasoning, that confidence should represent a calibrated \emph{probability of being correct}, and the decision should remain robust when some agents are persistently unreliable. Existing \emph{council aggregation} methods fail on both fronts: their confidence estimates measure decisiveness rather than correctness, and they cannot identify or discount persistently unreliable agents. We introduce Bayesian Dialectical Argumentation (BDA), which treats the council's \emph{typed} moves---who proposed, challenged, or conceded which answer---as observations of a classical annotator model with \emph{per-agent} reliabilities. This formulation recasts multi-agent deliberation as a reliability estimation problem, using the deliberation trace to infer agent reliability under persistent adversarial behavior. By weighting evidence according to inferred agent reliability, BDA yields calibrated posterior probabilities over candidate answers while allowing persistently unreliable agents to be inverted rather than merely outvoted. Across binary and multi-class benchmarks, BDA achieves the best calibration among zero-cost council aggregation methods, requiring no additional LLM calls, and improves robustness under persistent adversarial coalitions while remaining competitive in clean settings.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02005 — 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 2026-10-06T10:21:27.990Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).