Multi-Agent Debate

Follow this topic Ask about this topic

Multi-agent debate examines whether language models can reason more reliably by proposing answers, sharing evidence, challenging peers, and revising judgments. Common approaches assign roles such as advocate, critic, and judge; use retrieval and structured evidence checks; or adapt who communicates and when debate stops. Researchers apply these methods to mathematics, question answering, fact-checking, and medical or legal decisions, but results vary across tasks and model groups. A central tension is that debate can uncover errors when agents contribute useful independent information, yet consensus can also spread mistakes, suppress dissent, and add substantial cost.

Latest papers

144 papers19 papers in the last four weeks, up 6% on the four weeks before. 0.1% of all new papers.

May 26, 2026

PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate

Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduce persistent positional biases, amplify unreliable agents, and cause high sensitivity to role assignments. We introduce Permutation-Equivariant Adaptive Routing Multi-Agent Debate (PEAR), an inference-time train-free protocol that dynamically reconfigures communication roles and sparse topologies across consecutive debate rounds. By strategically switching agent-to-role assignments based on evolving agent states, PEAR prevents any agent from permanently occupying a privileged network position or distributes influence more evenly across the debate. We theoretically characterize PEAR as an equivariant sparse router: it preserves accuracy under agent relabeling while reducing routing complexity and improving generalization. Comprehensive empirical evaluations across four reasoning benchmarks and six diverse LLM backbones demonstrate PEAR significantly improves average accuracy over the strongest debate baselines. The code is available at https://github.com/EVIEHub/PEAR.

Yang Feng, Ziwei Xu, Xia Hu +1

University of Edinburgh · Shanghai AI Laboratory

Multi-Agent Debate Multi-Agent Systems Multi-Agent Reasoning Multi-Agent Communication

May 26, 2026

Debate Helps Weak Judges Reward Stronger Models

Despite theoretical promise, debate as a scalable oversight protocol has produced mixed empirical results: gains in some settings, and null effects in others, especially when the judge does not have information hidden from it. We study proposer-critic debate in a stronger-debater/weaker-judge setting on programmatically verifiable code and logic tasks. Debate helps the judge over a consultancy baseline when the critic provides a usable advantage: the critic's classification ability must exceed the judge's, and the judge must treat critic speeches as claims to verify rather than testimony to summarize. On the three of five pairings where the condition holds, proposer-critic debate's gains are statistically significant over consultancy, and these pairings are the most capable model pairings. On the two non-responder pairings in our set, debate produces null effects, and judge verification rates drop by tens of percentage points once a critic enters the transcript. In these cases the critic's binary-classification ability and the judge's are within noise of each other, and the critic's disagreement is parsed as testimony rather than a claim to check. Ablating rebuttal rounds from debate produces no measurable change in judge performance: a single independent critique recovers the bulk of debate's benefit at lower inference cost. These findings suggest a cheaper primitive for training-free scalable oversight in verifiable domains (answer, critique, judge) and a pre-deployment audit (does the critic beat the judge, and will the judge verify it?) that predicts when debate will help.

Ethan Elasky, Frank Nakasako, Naman Goyal

Palaestra Research · Independent

Scalable Oversight LLM-as-a-Judge Multi-Agent Debate Human Oversight of AI Reasoning Verification

May 21, 2026

SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate

Multi-Agent Debate (MAD) improves LLM-agent accuracy but suffers from rapid context growth, limiting scalability in larger multi-agent settings. Existing methods prune low-utility communications using prior signals, such as token-level log-likelihoods or LLM self-reported confidence. However, these signals become unreliable under hallucination, degrading the accuracy of MAD methods that rely on them. We propose SVR-MAD, a Bayesian-inspired MAD framework that treats pre-debate signals as priors and debate outcomes as posterior-style evidence for estimating agent correctness. SVR-MAD uses this evidence to incrementally construct the communication graph, prioritizing agents whose answers survive peer challenges. Experiments across multiple LLMs and benchmarks show that SVR-MAD reduces token cost by up to 61% while matching or improving accuracy relative to the most accurate competing MAD baseline.

Weifan Jiang, Rana Shahout, Minghao Li +4

Harvard University

Multi-Agent LLM Systems Multi-Agent Debate Multi-Agent Communication

May 18, 2026

Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection

Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on hard ones. We adapt Wald's Sequential Probability Ratio Test (SPRT) as a plug-in compute governor for LLM debates. After each round, an LLM judge emits a [0,1] consensus score on the latest agent positions; a Wald monitor accumulates the log-likelihood ratio of "useful convergence" vs "not yet useful" under a Beta likelihood family, and stops when either boundary is crossed or returns a capped best-effort outcome at R_max. Under i.i.d. assumptions the rule inherits SPRT type-I/type-II error guarantees; in deployment the calibration itself is the more important object, since it estimates whether the judge score actually separates useful from unhelpful convergence in a given domain. We evaluate two tracks: (i) a Monte-Carlo study under calibrated Beta models characterising working curves, error rates, capping behaviour, and sensitivity; and (ii) a real-LLM evaluation on 200 attempted MMLU and 200 attempted GSM8K items with three heterogeneous agents (gpt-5, claude-opus-4-6, gemini-2.5-pro) and a claude-opus-4-6 judge, using disjoint 40-item calibration subsets. On GSM8K the rule stops in 1.01 average rounds (4.06 LLM calls) at 97.0% accuracy vs 99.0% for fixed-5 debate at 15 calls: a 3.7x call reduction at -2pp accuracy. On MMLU the calibrated KL collapses to about 0 and the rule caps on 99.5% of items at 2.1x cost. The takeaway is not that SPRT makes debate more accurate, but that a classical sequential test serves as a cheap compute-control and failure-detection layer for multi-agent LLM systems.

Andrea Morandi

Cisco Systems, Inc.

LLM Inference Efficiency Multi-Agent Debate Multi-Agent Consensus Sequential Hypothesis Testing

May 14, 2026

Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation

LLM-based agents are increasingly used to simulate deliberative interactions such as negotiation, conflict resolution, and multi-turn opinion exchange. Yet generated transcripts often do not reveal why an agent's stance changes: movement may reflect evidence uptake, anchoring, role drift, echoing, or changed prompt and retrieval context. We introduce the Belief Engine (BE), an auditable belief-update layer that treats "belief" as an evidential state over a proposition and exposes it as scalar stance. BE extracts arguments into structured memory and updates stance with a log-odds rule controlled by evidence uptake u and prior anchoring a. Across multiple base LLMs, parameter sweeps show that these controls reliably shape stance dynamics while preserving an evidence-level update trail. On DEBATE, a human deliberation dataset with pre/post opinions, BE best reconstructs participants whose final stance follows extracted evidence; stable and evidence-opposed cases instead point to anchoring or factors outside the extracted evidence stream. BE provides configurable infrastructure for studying evidence-grounded deliberation, where openness, commitment, convergence, and disagreement can be tied to explicit update assumptions rather than hidden prompt effects.

Joshua C. Yang, Maurice Flechtner, Damian Dailisan +1

ETH Zurich · ETH Zurich and Centre for Democracy Studies Aarau, University of Zurich · Massachusetts Institute of Technology

Belief Revision Evidence-Grounded Reasoning Multi-Agent Debate

May 14, 2026

Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification

Multimedia verification requires not only accurate conclusions but also transparent and contestable reasoning. We propose a contestable multi-agent framework that integrates multimodal large language models, external verification tools, and arena-based quantitative bipolar argumentation (A-QBAF) as a submission to the ICMR 2026 Grand Challenge on Multimedia Verification. Our method decomposes each case into claim-centered sections, retrieves targeted evidence, and converts evidence into structured support and attack arguments with provenance and strength scores. These arguments are resolved through small local argument graphs with selective clash resolution and uncertainty-aware escalation. The resulting system generates section-wise verification reports that are transparent, editable, and computationally practical for real-world multimedia verification. Our implementation is public at: https://github.com/Analytics-Everywhere-Lab/MV2026_the_liems.

Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Hoang-Loc Cao +3

University of New Brunswick Fredericton, New Brunswick, Canada · FPT Software Quy Nhon, Vietnam · University of Science, VNU-HCM Ho Chi Minh City, Vietnam

Multi-Agent Debate Computational Argumentation

May 12, 2026

Multi-Agent Debate for Belief Optimization in Defeasible Domains

Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority voting accounts for most observed gains, and LLMs exhibit confidence escalation rather than calibration across rounds. We argue that the genuine value of debate, and dialectic systems as a whole, lies not in ground-truth tasks but in defeasible domains, where every position can in principle be defeated by better reasoning. We present the Council of Hierarchical Agentic Language (CHAL), a multi-agent dialectic framework that treats defeasible argumentation as an engine for belief optimization. Each agent maintains a CHAL Belief Schema (CBS), a graph-structured belief representation with a Bayesian-inspired architecture, that facilitates belief revision through a gradient-informed dynamic mechanism by leveraging the strength of the belief's thesis as a differentiable objective. Meta-cognitive value systems spanning epistemology, logic, and ethics are elevated to configurable hyperparameters governing agent reasoning and adjudication outcomes. We provide a series of ablation experiments that demonstrate systematic and interpretable effects: the adjudicator's value system determines the debate's overall trajectories in latent belief space, council diversity refines beliefs for all participants, and the framework generalizes across broad fields. CHAL is, to our knowledge, the first framework to treat multi-agent debate as structured belief optimization over defeasible domains. Further, the auditable belief artifacts it produces establish the foundation for dedicated evaluation suites for defeasible argumentation, with broader implications for building AI systems whose reasoning and value commitments are transparent, aligned, and subject to human oversight.

Tommaso Giovannelli, Griffin D. Kent

Belief Revision Multi-Agent LLM Systems Multi-Agent Debate Computational Argumentation Multi-Agent Deliberation

May 12, 2026

Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations

Unconstructive debate and uncivil communication carry well-documented costs for productivity and cohesion, yet isolating their effect on operational efficiency has proven difficult. Human subject research in this domain is constrained by ethical oversight, limited reproducibility, and the inherent unpredictability of naturalistic settings. We address this gap by leveraging Large Language Model (LLM) based Multi-Agent Systems as a controlled sociological sandbox, enabling systematic manipulation of communicative behavior at scale. Using a Monte Carlo simulation framework, we generate thousands of structured 1-on-1 adversarial debates across varying toxicity conditions, measuring convergence time, defined as the number of rounds required to reach a conclusion, as a proxy for interactional efficiency. Building on a prior study, we replicate and extend its findings across two additional LLM agents of varying parameter size, allowing us to assess whether the effects of toxic behavior on debate dynamics generalize across model scale. The convergence latency of 25% reported in the previous study was confirmed. It was found that this latency is significantly bigger for models with fewer parameters. We further identify a significant first-mover advantage, whereby the agent initiating the discussion wins significantly above chance regardless of toxicity condition.

Alison Moldovan-Mauer, Benedikt Mangold

Technische Hochschule Nürnberg Georg Simon Ohm 90489 Nuremberg, Germany

Multi-Agent Debate Multi-Agent Communication

May 10, 2026

Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols

When should a language model answer directly, sample and vote, or engage in multi-agent debate? Recent work shows voting often explains much of the gain attributed to debate, while selective-debate systems activate deliberation only on uncertain examples. We ask: under a matched ceiling on generated tokens (960 per example), how much per-example routing headroom exists, and how much is recoverable from cheap pre-deliberation signals? We evaluate greedy decoding, three-sample voting, and a two-agent critique-revise debate on MuSiQue and GSM8K using Llama 3.1 8B Instruct and Ministral 3 8B Instruct. On MuSiQue, an oracle selecting the correct protocol per example gains +14.0 and +13.7 pp over the best fixed one. The best fixed protocol is model- and dataset-dependent: each (model, dataset) cell has a different winner. This headroom is hard to recover from cheap ex-ante signals. A vote-entropy threshold is the only controller that directionally beats the best fixed protocol on both models (+1.3 and +1.7 pp), though individual paired-bootstrap CIs include zero. A joint analysis (meta-analysis +1.6 pp, p=0.125; Bayesian P(both>0)=0.59) is directionally consistent but not significant. Learned controllers (LR, GBT) do not outperform the threshold. The key finding is structural: vote entropy predicts where debate is safe, not where debate is needed. High entropy sharply reduces debate backfire, but 66% of debate-helpful examples (31/47) occur when voting is unanimous but wrong. A single-prompt self-critique probe on Llama flips the answer in 127/127 unanimous cases, yielding zero mutual information with the debate-helpful label; we cannot rule out a prompt-compliance artifact, but either interpretation disqualifies the probe as a router. Recovering the remaining headroom requires behavioral probes that avoid format-compliance confounds at the 8B scale.

Julia Hu, Alfred Shen, Kumar Lakshmipathi

Amazon Web Services

LLM Evaluation Multi-Agent Debate LLM Decision-Making Inference-Time Compute Allocation Majority Voting

May 10, 2026

EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium

Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulnerability: a single corrupted entry can contaminate the downstream memory-augmented reasoning, and debate alone fails to filter such errors. Existing safeguards filter entries via heuristics or LLM-based validation, yet they rely on AI judgments that share the same failure modes and overlook the cross-agent dynamics of MAD. We address this gap by formulating memory updating in MAD as a zero-trust memory game, in which no agent is assumed reliable and the game's equilibrium motivates a principled objective for calibrating memory influence. Guided by this objective, we propose EquiMem, an inference-time calibration mechanism that evaluates each update against the shared memory state and the memory already being used by other agents, using their existing retrieval queries and traversal paths as evidence of calibration. EquiMem instantiates this calibration for both embedding- and graph-based memory, and across diverse benchmarks, MAD frameworks, and memory architectures, it consistently outperforms existing safeguards, remains robust under adversarial agents, and incurs negligible inference overhead.

Yuqiao Meng, Luoxi Tang, Sakshi Sunil Narvekar +4

Binghamton University, State University of New York, Binghamton, NY, USA · University of Iowa, Iowa City, IA, USA

Multi-Agent Debate Agent Memory Poisoning Multi-Agent Systems Agent Memory Management Shared-Memory Multi-Agent Systems

May 8, 2026

MAVEN: Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing

While explicit reasoning trajectories enhance model interpretability, existing paradigms often rely on monolithic chains that lack intermediate verification, allowing early errors to cascade unchecked. This lack of modularity impedes granular auditing and compromises the epistemic trust required for high-stakes applications. We propose MAVEN (Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing), a blackboard-inspired framework designed to transform LLMs into deliberate reasoners through explicit role-decoupling. At its core, MAVEN operationalizes an adversarial Skeptic-Researcher-Judge loop, simulating expert deliberation by functionally separating logical defense from factual grounding. Experiments on OpenBookQA, TruthfulQA, HALUEVAL and StrategyQA benchmarks demonstrate that MAVEN delivers superior reasoning quality across four fine-grained metrics. Notably, MAVEN consistently outperforms latent reasoning models such as GEMINI-3.1-Pro and consensus-based baselines (e.g., ReConcile) by generating explicitly structured, modular, and verifiable deliberation trajectories, rather than relying on implicit internal states or post-hoc consensus. Moreover, comprehensive evaluations confirm that MAVEN is fully model-agnostic, serving as a strong and transferable reasoning booster that yields substantial performance improvements across diverse backbone models.

Yinsheng Yao, Jiehao Tang, Zhaozhen Yang +1

Tongji University Shanghai, China

LLM Auditing Multi-Agent Debate Multi-Agent Reasoning LLM Reasoning

May 7, 2026

Multi-agent decision making: A Blackwell's informativeness approach

The rapid development of large language models (LLMs) has motivated research on decision-making in multi-agent systems, where multiple agents collaborate to achieve shared objectives. Existing aggregation approaches, such as voting and debate, are largely ad-hoc and lack formal guarantees regarding the informativeness of the resulting decisions. In this paper, we provide a principled approach to analyse decisions made in the multi-LLM setting using Blackwell's informativeness framework. Within the Blackwell information-structure abstraction, we show that voting and debate induce information structures that are no more informative than the pooled private information of all agents. This result identifies Bayesian pooled posterior maximisation as an information-theoretic upper-bound decision rule under the Blackwell ordering. Motivated by this theoretical analysis, we introduce a practical method for LLM-based question-answering (QA) tasks that estimates each agent's posterior and approximates the pooled posterior using a product-of-posteriors estimator. Extensive experiments on six QA benchmarks demonstrate that our approach outperforms state-of-the-art multi-LLM debate and voting methods.

Zheng Zhang, Cuong C. Nguyen, Kevin Wells +1

Centre for Vision, Speech and Signal Processing, University of Surrey

Multi-Agent Debate Question Answering LLM Decision-Making

May 3, 2026

12 Angry AI Agents: Evaluating Multi-Agent LLM Decision-Making Through Cinematic Jury Deliberation

What if the twelve jurors of Sidney Lumet's 12 Angry Men (1957) were not men, but large language models? Would the one juror who disagrees still be able to change everyone's mind? This paper instantiates that scenario as a multi-agent benchmark for LLM deliberation: twelve agents, each conditioned on a film-faithful persona, debate the film's murder case using multi-agent framework. Two models representing opposite ends of the RLHF spectrum are tested: GPT-4o (closed-source, heavy alignment) and Llama-4-Scout (open-weight, lighter alignment), across three conditions (baseline, open-minded prompt, no initial vote), with N = 3 replications per cell (18 runs total). Three findings emerge. (i) Seventeen of eighteen runs end in a hung jury (a state where the jury fails to reach a unanimous verdict); the film's central event, gradual minority-to-majority persuasion, almost never occurs, indicating that anchoring is the dominant failure mode of current LLMs in this setting. (ii) The two models exhibit sharply different internal dynamics: GPT-4o produces a mean of 1.0 vote changes per run across all conditions, while Llama-4-Scout ranges from 2.0 (baseline) to 6.0 (open-minded prompt), and is the only model to reach a NOT_GUILTY verdict (1 of 3 runs in the no-initial-vote condition). The same ``open-minded'' instruction is internalized by Llama and ignored by GPT-4o. (iii) This asymmetry suggests that the intensity of RLHF alignment training, not model capability, is the primary determinant of deliberative flexibility in multi-agent settings. Flexibility, not capability, tracks human deliberation. The work is framed as an exploratory study and discusses implications for jury-of-LLMs evaluation and multi-agent debate.

Ahmet Bahaddin Ersoz

∗ORCID: 0000-0001-6297-7501

LLM Alignment LLM Agent Evaluation Multi-Agent Debate LLM Decision-Making

May 3, 2026

The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning

When copies of the same language model are prompted to debate, they produce diverse phrasings of one perspective rather than diverse perspectives. Multi-agent debate (MAD), and more broadly closed-system reasoning where agents iteratively transform each other's outputs, tends to preserve answer accuracy while degrading the reasoning behind those answers. We name the multi-agent case the Debate Trap and the broader phenomenon the Reasoning Trap, offering a programmatic theory of evidence-grounded reasoning failure.The framework has three parts: (i) SFS (Supported Faithfulness Score), a claim-level metric verifying decomposed atomic claims against provided evidence (decomposer-invariant rankings: Spearman rho=1.0); (ii) EGSR (Evidence-Grounded Socratic Reasoning), replacing adversarial argumentation with evidence-grounded inquiry; (iii) Theorem 1 (DPI Bound): under standard MAD, the chain E -> O^0 -> O^1 -> ... is Markov, and the Data Processing Inequality implies E[I(E;O^{t+1})] <= E[I(E;O^t)]. Three companion results -- open-system recovery (Theorem 2), EGSR accumulation (Lemma 2), and vote-aggregation floor (Proposition 1) -- partition multi-step LLM reasoning by its information-theoretic relationship to E. Across 16 conditions on SciFact (300 claims) and FEVER (1,000 claims), DebateCV (C13) preserves 88% of baseline accuracy while SFS drops 43%; majority-vote MAD (C15) reduces SFS to 1.7% of baseline (p < 10^{-6}, d = -0.96); EGSR recovers 98%. An R6 cohort study (Korean n=10x30 FEVER; English n=3x200 SciFact) finds inter-rater Fleiss kappa <= +0.018 with 0.8-1.4 Likert intra-rater shifts across language and domain -- the human agreement that faithfulness metrics have been calibrated against is not itself stable. We offer one falsifiable conjecture: any closed-system reasoning protocol preserving Theorem 1's Markov structure is, in expectation, subject to the same DPI bound.

Kwan Soo Shin

PolymathMinds AI Lab

Reasoning Evaluation Evidence-Grounded Reasoning Faithfulness of Language Model Reasoning Multi-Agent Debate LLM Reasoning

May 2, 2026

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate

On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inherits the error. OPD also remains largely unexplored in agentic tasks, where per-step errors compound across long trajectories and destabilize training. We propose MAD-OPD (Multi-Agent Debate-driven On-Policy Distillation), which breaks this ceiling by recasting the distillation teacher as a deliberative collective of teachers that debate over the student's on-policy state; the debate produces an emergent collective intelligence that supplies token-level supervision, with each teacher's contribution weighted by its post-debate confidence. To extend OPD to agentic tasks, we also introduce On-Policy Agentic Distillation (OPAD), which adds step-level sampling to stabilize training under multi-step error compounding. We additionally derive a task-adaptive divergence principle, selecting JSD (Jensen-Shannon divergence) for agentic stability and reverse KL (Kullback-Leibler) divergence for code generation, and verify it both theoretically and empirically. Across six teacher-student configurations (Qwen3 and Qwen3.5; 1.7B-14B students, 8B-32B teachers) and five agentic and code benchmarks, MAD-OPD ranks first across all six configurations; on the 14B+8B

\to

4B setting it lifts the agentic average by

+2.4\%

and the code average by

+3.7\%

over the stronger single-teacher OPD.

Jianze Wang, Ying Liu, Jinlong Chen +7

School of Artificial Intelligence and Automation, Huazhong University of Science and Technology · Alibaba Group

Multi-Agent Debate Multi-Teacher Knowledge Distillation LLM Agent Training On-Policy Distillation Teacher-Student Learning

Apr 29, 2026

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate

Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review filters hallucinations. Yet the failure dynamics of homogeneous debate remain poorly understood, therefore we report findings from a controlled empirical study of teams of

N{=}10

homogeneous agents (Qwen2.5-7B, Llama-3.1-8B, Ministral-3-8B) across

R{=}3

debate rounds on two high-difficulty benchmarks (GSM-Hard and MMLU-Hard). We compare peer debate against isolated self-correction and a stochastic noise control that injects rationales from unrelated problems. We decompose debate failure into three model-dependent pathways: sycophantic conformity, where agents uncritically adopt majority answers (modal adoption up to 85.5%); contextual fragility, where peer rationales destabilize previously correct reasoning (vulnerability rate up to 70.0%); and consensus collapse, where plurality voting discards correct answers already present in the generation pool (oracle gap up to 32.3 percentage points). Ablations over communication density (

K \in \{2,4,9\}

) and sampling temperature (

T \in \{0.4, 0.7\}

) show that conformity reaches high levels at minimal peer exposure (

K{=}2

) and intensifies with greater initial diversity. Across all configurations, debate consumes 2.1-3.4

\times

more tokens (up to 28,631 tokens per problem) than self-correction for equal or lower accuracy. Our results indicate that, within the 7-8B parameter class, homogeneous teams without structured roles do not benefit from unguided peer exchange, and that isolated self-correction consistently offers a more favorable cost-accuracy tradeoff.

Blaž Bertalanič, Carolina Fortuna

Jožef Stefan Institute Ljubljana, Slovenia

LLM Self-Correction AI Agent Evaluation Multi-Agent Debate Multi-Agent Consensus

Apr 29, 2026

A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection

Stance detection identifies the attitude of a text author toward a given target. Recent studies have explored various LLM-based strategies for this task, from zero-shot prompting to multi-agent debate. However, existing works differ in data splits, base models, and evaluation protocols, making fair comparison difficult. We conduct a systematic comparison that evaluates five methods across two categories -- prompt-based inference (Direct Prompting, Auto-CoT, StSQA) and agent-based debate (COLA, MPRF) -- on four datasets with 14 subtasks, using 15 LLMs from six model families with parameter sizes from 7B to 72B+. Our experiments yield several findings. First, on all models with complete results, the best prompt-based method outperforms the best agent-based method, while agent methods require 7 to 12 times more API calls per sample. Second, model scale has a larger impact on performance than method choice, with gains plateauing around 32B. Third, reasoning-enhanced models (DeepSeek-R1) do not consistently outperform general models of the same size on this task.

Genan Dai, Zini Chen, Yi Yang +1

School of Artificial Intelligence, Shenzhen Technology University, Shenzhen, China

Multi-Agent LLM Systems LLM Evaluation Stance Detection LLM Prompting Multi-Agent Debate

Apr 28, 2026

From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling

Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requirements remains challenging for current large language models (LLMs). In this paper, we propose Agora-Opt, a modular agentic framework for optimization modeling that combines decentralized debate with a read-write memory bank. Agora-Opt allows multiple agent teams to independently produce end-to-end solutions and reconcile them through an outcome-grounded debate protocol, while memory stores solver-verified artifacts and past disagreement resolutions to support training-free improvement over time. This design is flexible across both backbones and methods: it reduces base-model lock-in, transfers across different LLM families, and can be layered onto existing pipelines with minimal coupling. Across public benchmarks, Agora-Opt achieves the strongest overall performance among all compared methods, outperforming strong zero-shot LLMs, training-centric approaches, and prior agentic baselines. Further analyses show robust gains across backbone choices and component variants, and demonstrate that decentralized debate offers a structural advantage over centralized selection by enabling agents to refine candidate solutions through interaction and even recover correct formulations when all initial candidates are flawed. These results suggest that reliable optimization modeling benefits from combining collaborative cross-checking with reusable experience, and position Agora-Opt as a practical and extensible foundation for trustworthy optimization modeling assistance. Our code and data are available at https://github.com/CHIANGEL/Agora-Opt.

Jianghao Lin, Zi Ling, Chenyu Zhou +4

Antai College of Economics and Management, Shanghai Jiao Tong University · University of Chicago Booth School of Business · School of Economics and Management, Tsinghua University +1

Multi-Agent Debate Multi-Agent LLMs Natural Language to Optimization Modeling Memory-Augmented Language Model Agents

Apr 27, 2026

Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a framework that distills multi-agent debate into a single LLM through a two-stage fine-tuning pipeline combining debate structure learning with internalization via dynamic reward scheduling and length clipping. Across multiple models and benchmarks, our internalized models match or exceed explicit multi-agent debate performance using up to 93% fewer tokens. We then investigate the mechanistic basis of this capability through activation steering, finding that internalization creates agent-specific subspaces: interpretable directions in activation space corresponding to different agent perspectives. We further demonstrate a practical application: by instilling malicious agents into the LLM through internalized debate, then applying negative steering to suppress them, we show that distillation makes harmful behaviors easier to localize and control with smaller reductions in general performance compared to steering base models. Our findings offer a new perspective for understanding multi-agent capabilities in distilled models and provide practical guidelines for controlling internalized reasoning behaviors. Code available at https://github.com/johnsk95/latent_agents

John Seon Keun Yi, Aaron Mueller, Dokyun Lee

Boston University

Multi-Agent Debate Language Model Distillation Multi-Agent Reasoning

Apr 22, 2026

Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design

Text-guided molecular design is a key capability for AI-driven drug discovery, yet it remains challenging to map sequential natural-language instructions with non-linear molecular structures under strict chemical constraints. Most existing approaches, including RAG, CoT prompting, and fine-tuning or RL, emphasize a small set of ad-hoc reasoning perspectives implemented in a largely one-shot generation pipeline. In contrast, real-world drug discovery relies on dynamic, multi-perspective critique and iterative refinement to reconcile semantic intent with structural feasibility. Motivated by this, we propose Mol-Debate, a generation paradigm that enables such dynamic reasoning through an iterative generate-debate-refine loop. We further characterize key challenges in this paradigm and address them through perspective-oriented orchestration, including developer-debater conflict, global-local structural reasoning, and static-dynamic integration. Experiments demonstrate that Mol-Debate achieves state-of-the-art performance against strong general and chemical baselines, reaching 59.82% exact match on ChEBI-20 and 50.52% weighted success rate on S

^2

-Bench. Our code is available at https://github.com/wyuzh/Mol-Debate.

Wengyu Zhang, Xiao-Yong Wei, Qing Li

♠The Hong Kong Polytechnic University · ♡Sichuan University

AI-Assisted Scientific Research Multi-Agent Debate Molecular Generation Drug Discovery Molecule Design

Apr 21, 2026

Durable Evaluation Framework: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

RLHF-trained models are systematically biased toward agreement over accuracy, a structural property of the training process. We present Durable Evaluation Framework (DEF) Arbitration, a multi-agent architecture that mitigates identity-framed sycophancy by arbitrating between two models tuned to opposing DEFs, with a pragmatist synthesizer evaluating both arguments blind to their origins. This paper evaluates a prompt-based instantiation of DEF Arbitration. The key mechanisms are static DEF tuning, identity stripping before synthesis, single-round independent argumentation, and blind arbitration. We evaluate five instantiations on 200 stratified questions from SycophancyEval. All tested DEF variants (AnCifer, DeWin, FeynStein, BurGal, Trident) significantly outperform the single-model baseline (18.5%) and instructed-opposition baseline (29.0%), with DeWin achieving 48.5% accuracy (z=6.36, p<0.001 versus both). The variants are not significantly different from each other at n=200. The BurGal variant achieves 53.0% but functions as an architectural validity check; its consensus/heterodox axis structurally favors the heterodox model on every benchmark question. A pre-training floor affects an estimated 40% of questions; fine-tuned DEF models are the identified next step.

Sam Ryan

Novel Systems Engineering LLC

LLM Sycophancy Multi-Agent Debate Language Model Bias Evaluation

Apr 21, 2026

Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification. The code is available at https://github.com/tangyixuan/RADAR.

Yixuan Tang, Yirui Zhang, Hang Feng +1

School of Computing, National University of Singapore

Multi-Agent Debate Automated Fact-Checking

Apr 18, 2026

DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection

The rapid evolution of video generation technologies poses a significant challenge to media forensics, as conventional detection methods often fail to generalize beyond their training distributions. To address this, we propose DVAR (Debate-based Video Authenticity Reasoning), a training-free framework that reformulates video detection as a structured multi-agent forensic reasoning process. Moving beyond the paradigm of pattern matching, DVAR orchestrates a competition between a Generative Hypothesis Agent and a Natural Mechanism Agent. Through iterative rounds of cross-examination, these agents defend their respective explanations against abnormal evidence, driving a logical convergence where the truth emerges from rigorous stress-testing. To adjudicate these conflicting claims, we apply Occam's Razor through the Minimum Description Length (MDL) framework, defining an Explanatory Cost to quantify the "logical burden" of each reasoning path. Furthermore, we integrate GenVideoKB, a dynamic knowledge repository that provides high-level reasoning heuristics on generative boundaries and failure modes. Extensive experiments demonstrate that DVAR achieves competitive performance against supervised state-of-the-art methods while exhibiting superior generalization to unseen generative architectures. By transforming detection into a transparent debate, DVAR provides explicit, interpretable reasoning traces for robust video authenticity assessment.

Hongyuan Qi, Feifei Shao, Ming Li +2

Zhejiang University Hangzhou, Zhejiang, China · Guangming Lab Shenzhen, Guangdong, China

Multi-Agent Debate Deepfake Detection

Apr 15, 2026

Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration

Fairness in language models is typically studied as a property of a single, centrally optimized model. As large language models become increasingly agentic, we propose that fairness emerges through interaction and exchange. We study this via a controlled hospital triage framework in which two agents negotiate over three structured debate rounds. One agent is aligned to a specific ethical framework via retrieval-augmented generation (RAG), while the other is either unaligned or adversarially prompted to favor demographic groups over clinical need. We find that alignment systematically shapes negotiation strategies and allocation patterns, and that neither agent's allocation is ethically adequate in isolation, yet their joint final allocation can satisfy fairness criteria that neither would have reached alone. Aligned agents partially moderate bias through contestation rather than override, acting as corrective patches that restore access for marginalized groups without fully converting a biased counterpart. We further observe that even explicitly aligned agents exhibit intrinsic biases toward certain frameworks, consistent with known left-leaning tendencies in LLMs. We connect these limits to Arrow's Impossibility Theorem: no aggregation mechanism can simultaneously satisfy all desiderata of collective rationality, and multi-agent deliberation navigates rather than resolves this constraint. Our results reposition fairness as an emergent, procedural property of decentralized agent interaction, and the system rather than the individual agent as the appropriate unit of evaluation.

Sayan Kumar Chaki, Antoine Gourru, Julien Velcin

Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · École Centrale de Lyon, LIRIS CNRS UMR 5205

Demographic Bias in Language Models Multi-Agent Systems Multi-Agent Debate

Apr 15, 2026

Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate

Entity alignment (EA) aims to identify entities referring to the same real-world object across different knowledge graphs (KGs). Recent approaches based on large language models (LLMs) typically obtain entity embeddings through knowledge representation learning and use embedding similarity to identify an alignment-uncertain entity set. For each uncertain entity, a candidate entity set (CES) is then retrieved based on embedding similarity to support subsequent alignment reasoning and decision making. However, the reliability of the CES and the reasoning capability of LLMs critically affect the effectiveness of subsequent alignment decisions. To address this issue, we propose AgentEA, a reliable EA framework based on multi-agent debate. AgentEA first improves embedding quality through entity representation preference optimization, and then introduces a two-stage multi-role debate mechanism consisting of lightweight debate verification and deep debate alignment to progressively enhance the reliability of alignment decisions while enabling more efficient debate-based reasoning. Extensive experiments on public benchmarks under cross-lingual, sparse, large-scale, and heterogeneous settings demonstrate the effectiveness of AgentEA.

Cunda Wang, Ziying Ma, Po Hu +2

Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, China · School of Computer Science, Central China Normal University, Wuhan, China · National Language Resources Monitoring and Research Center for Network Media, Central China Normal University, Wuhan, China +3

Multi-Agent Debate KG Embedding

Apr 14, 2026

Multi-Persona Debate System for Automated Scientific Hypothesis Generation

Modern scientific discovery is bottlenecked not by data scarcity, but by the inability to synthesize fragmented knowledge into actionable hypotheses. This challenge is especially acute in battery materials research, where electrochemical performance, interfacial behavior, and manufacturing feasibility must be optimized simultaneously. Here, we present the Multi-Persona Debate System (MPDS), a literature-grounded framework for automated scientific hypothesis generation that combines literature retrieval, long-context large language model reasoning, corpus-driven persona induction, and structured multi-agent debate. MPDS constructs literature snapshots of up to 500 papers, grounds agents in role-specific evidence pools, and conducts a three-round citation-aware debate followed by moderator synthesis, enabling negotiation between personas while preserving evidence traceability. We evaluate MPDS using a temporally controlled protocol excluding direct access to target papers, including two held-out battery-materials case studies and a blinded comparison across 30 matched cases. In sodium-ion anode and all-solid-state battery cathode design tasks, MPDS recovered design logics aligned with experimentally validated solution spaces and generated more mechanistically explicit, process-aware proposals than simpler baselines. To assess the impact of personas and debate, we introduce Integrative Hypothesis Quality scoring. In ablation studies, MPDS achieved the highest mean score among five conditions, with its largest advantage in cross-perspective integration. A laboratory follow-up suggests utility as a diagnostic aid for identifying practical bottlenecks in workflows. These results indicate that structured debate over literature snapshots improves hypothesis formation under coupled engineering constraints and provides a reusable workflow for text-intensive scientific discovery.

Jaeha Oh, Byungchan Kim, Ju Li +2

Department of Materials Science & Engineering, Ajou University, Suwon 16499, Republic of Korea · Department of Energy Systems Research, Ajou University, Suwon 16499, Republic of Korea · Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA +3

Scientific Hypothesis Generation Evidence-Grounded Generation Multi-Agent Debate

Apr 14, 2026

CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature escalations to costlier models or experts due to under-confidence and inefficient compute scaling. CascadeDebate addresses this gap by inserting multi-agent deliberation directly at each tier's escalation boundary. Confidence-based routers activate lightweight agent ensembles only for uncertain cases, enabling consensus-driven resolution of ambiguities internally without invoking higher-cost upgrades. Our unified architecture alternates single-model inference with selective multi-agent deliberation across model scales, culminating in human experts as the final fallback. This design scales test-time compute dynamically according to query difficulty. Across five benchmarks spanning science, medicine, and general knowledge, CascadeDebate outperforms strong single-model cascades and standalone multi-agent systems by up to 26.75 percent. An online threshold optimizer proves essential, boosting accuracy by 20.98 to 52.33 percent relative improvement over fixed policies and enabling elastic adaptation to real-world distributions.

Raeyoung Chang, Dongwook Kwon, Jisoo Lee +1

Sogang University · Kwangwoon University · Seoul National University +1

LLM Routing Multi-Agent Debate Test-Time Scaling

Apr 13, 2026

Collective Opinion Dynamics in Structured LLM Populations

Large Language Models are increasingly deployed as interacting agents in settings such as online platforms, recommendation systems, and multi-agent applications. Understanding the collective behaviors that emerge from their interactions is therefore increasingly crucial, especially as these behaviors may shape public opinion and contribute to polarization. In this work, we investigate how network structure and group composition shape the evolution of opinions in populations of LLM agents engaged in multi-round debates. We generate networks with controlled levels of homophily and varying group sizes, and perform ten independent runs per configuration. The results show that LLM agents exhibit patterns that are highly sensitive to network structure, relative group sizes, and to the model itself. We highlight that even within LLM populations, low homophily facilitates convergence by increasing opportunities for cross-group interaction, whereas higher homophily limits cross-group exposure and can preserve distinct opinion states, consistent with previous research. We further show that the choice of LLM substantially affects the resulting dynamics, with different models exhibiting different patterns of opinion updating under comparable network conditions. At the individual level, providing agents with information about their local neighborhood further modulates opinion transitions, revealing substantial differences between models in their sensitivity to local social context. Overall, our findings show that the collective dynamics of LLM populations arise from interactions among model-specific behavior, network structure, population composition, and local social information.

Erica Cau, Andrea Failla, Giulio Rossetti

Department of Computer Science, University of Pisa · ISTI-CNR

Multi-Agent LLM Systems Opinion Dynamics Multi-Agent Debate Agent-Based Modeling

Apr 13, 2026

Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate

Multimodal Large Language Models (MLLMs) in healthcare suffer from severe confirmation bias, often hallucinating visual details to support initial, potentially erroneous diagnostic hypotheses. Existing Chain-of-Thought (CoT) approaches lack intrinsic correction mechanisms, rendering them vulnerable to error propagation. To bridge this gap, we propose Dialectic-Med, a multi-agent framework that enforces diagnostic rigor through adversarial dialectics. Unlike static consensus models, Dialectic-Med orchestrates a dynamic interplay between three role-specialized agents: a proponent that formulates diagnostic hypotheses; an opponent equipped with a novel visual falsification module that actively retrieves contradictory visual evidence to challenge the Proponent; and a mediator that resolves conflicts via a weighted consensus graph. By explicitly modeling the cognitive process of falsification, our framework guarantees that diagnostic reasoning is tightly grounded in verified visual regions. Empirical evaluations on MIMIC-CXR-VQA, VQA-RAD, and PathVQA demonstrate that Dialectic-Med not only achieves state-of-the-art performance but also fundamentally enhances the trustworthiness of the reasoning process. Beyond accuracy, our approach significantly enhances explanation faithfulness and decisively mitigates hallucinations, establishing a new standard over single-agent baselines.

Zhixiang Lu, Jionglong Su

Xi’an Jiaotong-Liverpool University

VLM Hallucination Mitigation Medical VLMs Medical VQA Multi-Agent Debate Counterfactual Reasoning in Language Models

Apr 12, 2026

BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection

Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses; when the experts disagree, a structured counter-argumentation round and cross-source adjudication resolve the conflict, followed by a cascading safety layer that filters common false-positive patterns. We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families. Experimental results show that BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines. Further analyses across six backbone models and two prompting strategies confirm that retrieval augmentation and structured debate are complementary, and that the framework benefits most from models with sufficient instruction-following and clinical language understanding.

Saukun Thika You, Nguyen Anh Khoa Tran, Wesley K. Marizane +3

Department of Computer Science, University of Memphis, Memphis, United States · Department of Computer Information Systems, Alabama State University, Montgomery, United States

Language Model Error Detection Multi-Agent Debate Medical LLMs Retrieval-Augmented Generation