This work presents a systematic literature review characterizing 141 primary studies on Multi-Agent Debate, and derives a three-dimensional taxonomy covering debate participants, the interaction mechanisms structuring the exchange, and the agreement protocols governing debate resolution, supported by formal notations to render MAD configurations.
Abstract
Multi-Agent Debate (MAD) is a promising paradigm for improving the accuracy and robustness of Large Language Model (LLM)-based agentic systems. It enables multiple agents to exchange arguments, critique each other's outputs, and iteratively converge towards a solution. However, research remains fragmented, with inconsistent terminology and no rigorous synthesis of MAD design dimensions. We present a systematic literature review characterizing 141 primary studies on MAD. We derive a three-dimensional taxonomy covering debate participants, the interaction mechanisms structuring the exchange, and the agreement protocols governing debate resolution, supported by formal notations to render MAD configurations. Our analysis reveals that the field has implicitly converged on a narrow design pattern - static, fully connected topologies, verbatim exchange, short-term memory and voting resolution strategies - adopted by convention rather than systematic comparison, while promising alternatives remain marginal. Because any MAD setting reflects roughly a dozen interacting design decisions, cross-study comparison is unreliable when these are left implicit. We position the taxonomy as a descriptive map of the research landscape, a framework for controlled benchmarking, and potentially as a schema for machine-readable MAD specifications. As future work, we propose formalizing it into an executable specification, enabling cost-aware benchmarking and automated tuning of debate configurations.
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.
Wentao Hu, Zhuoyue Wan, Jin-Hao Shen et al.· 0 citations
This study proposes a moderated, domain-adaptive multi-agent debate framework applied to the high-stakes domain of satellite communications (SatCom), and assesses the efficacy of structured deliberation against single-agent baselines, and the impact of model heterogeneity versus homogeneity.
Susana Gómez Álvarez, Alejandro Mozo Quesada, Tomás Navarro et al.· Journal of Intelligence and...· 0 citations
Multi-agent debate, in which several LLMs exchange arguments before answering, is widely assumed to improve answer quality by surfacing genuine disagreement. That mechanism is rarely checked. We introduce four measurements: (A) the agreement a debater reports; (B) whether its reply text actually pushes back; (C) whether the position persists once the eliciting instruction is removed; and (D) for open-weight models, the stance response in the debater's own token log-probabilities. We evaluate three-model committees debating open-ended GlobalOpinionQA across 750 debates under three tones: friendly (seek common ground), neutral, and hostile (stress-test every position). (A) Tone strongly reshapes reported agreement: full agreement differs by 50.4 percentage points between the friendly and hostile endpoints. (B) A judge that reads only the reply text, never the self-report or the condition, recovers the same pattern. (C) The dissent appears partly tied to the instruction that elicited it: labels revert toward agreement 23.1 points more often after deleting the hostile instruction than under a matched re-ask that keeps it; question-weighted inference is inconclusive on first-round turns alone (p=0.0625), significant pooling all rounds (p=0.016), and only 11/28 first-round reversions also appear in the reply text. (D) Opposing arguments weaken a debater's stance margin more consistently than they shift its direction. For final answers we detect no quality gain: a bias-checked jury returns 299/299 ties (ruling out only large differences), accuracy on a verifiable control task is unchanged, and a jury without the bias check had declared debate the winner 66% of the time -- an artifact of reading order. Taken together, LLM debate readily changes what agents say, but we find much weaker evidence that it changes what they persistently endorse or improves the quality of the final answer.
This work identifies the emergence of collective norms in multi-agent LLM debates and finds that agent heterogeneity suppresses emergence by smoothing this transition, and shows that these insights generalize to realistic decision-making tasks, including investment decisions and LLM-as-a-judge evaluation.
It is demonstrated that multi-agent consensus can enforce artificial agreement at the expense of true human alignment at the expense of true human alignment, revealing a structural limitation in consensus-style, role-specialized MAD protocols for subjective scoring.
Mi-Ra Song, Chanwoo Kim, Sugyeong Eo et al.· 0 citations
As scientific literature grows and papers increasingly under-report limitations, multi-agent LLMs offer a promising approach to systematically uncover these hidden failure modes. Here, we introduce Tree-of-Concerns, a multi-agent framework that deploys specialized skeptic personas, each operating through a category-specific analytical lens, as parallel debate trees to extract unstated limitations from scientific papers. Each persona conducts structured, evidence-grounded argumentation, while a Panel Review mechanism re-evaluates each surviving claim from all five perspectives to correct category drift and severity miscalibration. Through experiments on ToC-Bench, our benchmark of 414 research papers with 1,905 unstated limitations, sourced from reviewer-reported weaknesses and follow-up citation critiques, we demonstrate that ToC improves precision by 79% and coverage by 11% relative to strongest baselines, surfacing specific, evidence-grounded concerns that support reviewers in systematic evaluation.
