Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognition

• URL: http://arxiv.org/abs/2608.23029v1
• Date: Mon, 24 Aug 2026 09:33:53 GMT
• Title: Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognition
• Abstract summary: We cast moderation as a meta-cognitive process, monitoring debate utility, controlling deliberation, and adjudicating a final answer.<n>We introduce Meta-Moderator, a learnable framework that dynamically regulates debate and decides when to finalize an answer.
• Score: 18.85069182811407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent debate can improve large language model reasoning by eliciting diverse hypotheses and critiques, yet its performance is often constrained by weak moderation. Common pipelines rely on fixed budgets, agreement-based stopping, or untrained judges, leading to redundant deliberation and unreliable evidence aggregation. We cast moderation as a meta-cognitive process, monitoring debate utility, controlling deliberation, and adjudicating a final answer, and introduce Meta-Moderator, a learnable framework that dynamically regulates debate and decides when to finalize an answer. Meta-Moderator is trained independently of the debaters via outcome-driven policy optimization, making debate regulation an explicit capability rather than an incidental effect of prompting. Across five benchmarks, Meta-Moderator outperforms widely used decision layers and transfers across tasks and system configurations. Further analyses show that it allocates debate more selectively and reduces mis-aggregation after informative hypotheses appear.

Related papers

• A Theory of Post-hoc Debate Judgement [29.17703958536647]
  We develop and test a novel theory of debate judgement applicable to all settings where agents engage in debates.<n>We identify a number of formal properties that debate judgement may be required to satisfy in general, as concerns, robustness, groundedness and explainability.<n>We show that the two methods give similar accuracy performances but the former may lack formal guarantees.
  arXiv  Detail & Related papers  (2026-08-19T15:03:44Z)
• Multimodal Fact-Level Attribution for Verifiable Reasoning [80.60864342985748]
  Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation.<n>Existing multimodal grounding benchmarks and evaluation methods fail to assess attribution in complex multimodal reasoning.<n>We introduce MuRGAt, a benchmark for evaluating fact-level multimodal attribution in settings that require reasoning beyond direct observation.
  arXiv  Detail & Related papers  (2026-02-12T03:10:02Z)
• DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation [47.62978918069135]
  We introduce Dynamic Multi-Agent Debate (DynaDebate), which enhances the effectiveness of multi-agent debate through three key mechanisms.<n>Extensive experiments demonstrate that DynaDebate achieves superior performance across various benchmarks, surpassing existing state-of-the-art MAD methods.
  arXiv  Detail & Related papers  (2026-01-09T12:01:33Z)
• MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction [52.89860691282002]
  Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce.<n>Despite advances in multimodal large language models (MLLMs), implicit AVE remains challenging due to the complexity of multidimensional data.<n>We introduce textscmodelname, a multi-agent debate framework that employs multiple MLLM agents to iteratively refine inferences.
  arXiv  Detail & Related papers  (2025-10-07T06:27:42Z)
• Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate [30.66779902590191]
  Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability.<n>LLMs' inherent sycophancy can collapse debates into premature consensus.
  arXiv  Detail & Related papers  (2025-09-27T02:27:13Z)
• Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate [2.3027211055417283]
  We show that debate can lead to a decrease in accuracy over time.<n>Our analysis reveals that models frequently shift from correct to incorrect answers in response to peer reasoning.<n>These results highlight important failure modes in the exchange of reasons during multi-agent debate.
  arXiv  Detail & Related papers  (2025-09-05T13:47:38Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media [26.07883439550861]
  MV-Debate is a multi-view agent debate framework with dynamic reflection gating for unified multimodal harmful content detection.<n>MV-Debate assembles four complementary debate agents, a surface analyst, a deep reasoner, a modality contrast, and a social contextualist, to analyze content from diverse interpretive perspectives.
  arXiv  Detail & Related papers  (2025-08-07T16:38:25Z)
• Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents [13.626715532559079]
  We propose DebateCV, the first claim verification framework that adopts a debate-driven methodology using multiple LLM agents.<n>In our framework, two Debaters take opposing stances on a claim and engage in multi-round argumentation, while a Moderator evaluates the arguments and renders a verdict with justifications.<n> Experimental results show that our method outperforms existing claim verification methods under varying levels of evidence quality.
  arXiv  Detail & Related papers  (2025-07-25T09:19:25Z)
• Debating for Better Reasoning: An Unsupervised Multimodal Approach [56.74157117060815]
  We extend the debate paradigm to a multimodal setting, exploring its potential for weaker models to supervise and enhance the performance of stronger models.<n>We focus on visual question answering (VQA), where two "sighted" expert vision-language models debate an answer, while a "blind" (text-only) judge adjudicates based solely on the quality of the arguments.<n>In our framework, the experts defend only answers aligned with their beliefs, thereby obviating the need for explicit role-playing and concentrating the debate on instances of expert disagreement.
  arXiv  Detail & Related papers  (2025-05-20T17:18:17Z)
• Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate [85.3444184685235]
  We propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution. Our framework encourages divergent thinking in LLMs which would be helpful for tasks that require deep levels of contemplation.
  arXiv  Detail & Related papers  (2023-05-30T15:25:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.