Multi-Agent Deliberation

Follow this topic Ask about this topic

Latest papers

34 papers8 papers in the last four weeks, up 100% on the four weeks before. 0.0% of all new papers.

Oct 16, 2026

Discuss More, Comment Less: Boosting Automated Research via Multi-Perspective Collaborative Review

As automated research is increasingly adopted for writing papers, automated review has become a critical link between paper generation and quality control. However, existing methods largely rely on single-model feedback or simple review aggregation, failing to explicitly model expert responsibilities or collective deliberation in actual peer reviews, which limits effective cross-examination and reliable decision-making. Therefore, we formulate paper review as a computational modeling problem of peer review mechanisms and propose RoundtableReview, a deliberative multi-agent framework for enhancing automated research. RoundtableReview structures each paper into eight semantic slots and coordinates six academic and industry reviewers with complementary perspectives, retrieval sources, and specialized responsibilities. Through independent assessment, cross-examination, roundtable deliberation, dynamically weighted voting, and chair synthesis, the framework generates evidence-based and traceable feedback. Experiments on two automated research backbones show that the method improves paper quality in both backbones and outperforms baselines in automatic and human evaluations with fewer comments.

Junkai Zhou, Jiajia Wu, Zhaoyi Zhang +2

Automated Peer Review Multi-Agent Deliberation Autonomous Research Agents

Oct 16, 2026

On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management

Multi-criteria models for healthcare operations need weights that express how stakeholders trade off patient waiting time, provider workload, and operating cost, but these weights are difficult to quantify. Teams of large language model (LLM) agents, each prompted to represent a stakeholder, have been used to supply them. We propose a framework for assessing the reliability of LLM-generated preferences as inputs to multi-objective optimization and quantifying how their uncertainty affects decisions. We study explicit preferences by asking agents to rate the importance of the criteria in an outpatient appointment scheduling problem, and implicit preferences by inferring trade-offs from the agents' pairwise choices between emergency department configurations. The computational experiments show that the explicit preferences respond to the clinic's operating conditions and differ across roles, but deliberation among the agents can erase these differences, whereas simple averaging preserves them. The pairwise choices used to reveal the agents' implicit preferences depend largely on which option is presented first, and we find limited evidence that a statistical model using contextual information alongside presentation order predicts the agents' choices on new comparison pairs better than a model using presentation order alone. We then formulate robust weighted-sum optimization models to account for preference uncertainty. In most cases, these models select different schedules or configurations from those obtained using average preference weights. These results indicate that LLM-generated preferences need an audit of this kind before they are used as optimization weights in healthcare decision support.

Marco Boresta, Tommaso Giovannelli, Sepehr Namirad +1

Istituto di Analisi dei Sistemi ed Informatica (IASI), CNR, Rome, Italy · Department of Mechanical, Materials, and Industrial Engineering, University of Cincinnati, Cincinnati, OH · Department of Computer, Control, and Management Engineering (DIAG), Sapienza University of Rome, Rome, Italy

Preference Modeling Multi-Criteria Decision Analysis Healthcare Behavioral Consistency of LLM Agents Multi-Agent Deliberation

Oct 13, 2026

Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate

Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. However, standard broadcast-style MAD makes peer answers visible without requiring agents to engage with a particular peer claim. As a result, reliable reasoning may be suppressed by conflicting or majority responses, limiting achievable performance, while erroneous reasoning may persist and degrade final predictions without actionable feedback. We propose TrueMAD, a backbone-agnostic test-time plug-in that introduces one-to-one, free-form peer advice between answer broadcasting and self-revision. Each source agent responds to a target's current reasoning through support, rebuttal, refinement, or further questions, while the target retains control over how to revise. The same mechanism can augment standard MAD and its improved variants without parameter updates. Across AIME, GPQA-Diamond, and TruthfulQA with Qwen3-30B-A3B, TrueMAD improves agent-level and strict-majority accuracy over MAD by 3.62 and 3.52 percentage points on average, while TrueDMAD improves DMAD by 4.72 and 4.06 points, respectively. Analyses at the utterance, agent-transition, and group levels further show more peer-specific deliberation, more correction-oriented revisions, and more favorable consensus dynamics.

Dezheng Bao, Sihang Du, Renhong Huang +3

Zhejiang University

Multi-Agent Debate Multi-Agent Reasoning Multi-Agent Deliberation Multi-Agent Communication Multi-Agent Consensus

Oct 13, 2026

Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagreement or reasoning quality. We present an adaptive multi-agent controller (ADMA) that learns continuous policies for proposal, challenge, arbitration, and coordination while keeping the task model frozen. Shared trace features describe quality, agreement, and progress, while role-specific features support decentralized control during inference. One controller trained on legal and financial reasoning is transferred without policy updates to four textual and multimodal benchmarks and two successive task-model versions. With Qwen3.5 held fixed, ADMA-Full improves accuracy by 6.2-14.2 percentage points over Direct and by 2.8-3.0 points over ADMA-Fixed. Paired bootstrap ranges for the Full-Fixed comparison are positive on three tasks. Outcome decompositions show that recoveries exceed introduced errors, while process assessment records fewer false-consensus events and more supported correct outcomes. Transfer to Qwen3.6 remains task dependent, which bounds the generality of the learned policy. Median token and latency ratios are 14.3-18.7 and 7.8-16.5 relative to Direct. These results show that adaptive deliberation can improve fixed-model recognition when its task-dependent gains justify the additional computation.

Yuan Liu, Haoyue Peng, Fanliang Hu +2

Medical Artificial Intelligence Laboratory, Chongqing University Cancer Hospital, Chongqing University, Chongqing, 400030, China

Multi-Agent Deliberation Multi-Agent Debate Multi-Agent Systems Multi-Agent Coordination Language Model-Based Control

Oct 2, 2026

Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise

Multi-agent debate is increasingly used to reach consensus among LLM agents, yet agents often yield to a unanimous majority. When an agent changes its answer, has it changed its mind or only its statement? We study this with two-hop factual questions whose intermediate entity (the bridge, e.g. the country in "the capital of the country where the Sagrada Familia is located") is never stated by anyone. Scripted peers, in the role of Asch's confederates, unanimously assert a wrong answer taken from another fact with a different bridge. At the moment the agent answers, we read the bridge from its residual stream with the Jacobian lens (J-lens) and, for comparison, the logit lens. In pre-registered tests on held-out facts with four open-weight models, agents of Qwen3.5-4B, Qwen3.6-27B and Gemma-4-E4B-it that gave in still represented their original bridge in the pre-registered layers below the output (hit@100 above a control entity: 0.85, 0.22 and 0.24), where the logit lens rarely ranked it among the top 100 tokens (0.00-0.06). These agents also represented the bridge behind the peers' answer, beyond a mention baseline. A pre-registered addendum hid the agent's earlier answer or removed it: agents that gave in still represented their original bridge in all four models (0.43, 0.29, 0.37 and 0.25 with the answer hidden), including Llama-3.1-8B-Instruct, which barely did so with its answer in view (0.03). The premise can thus be computed from the question alone while the agent states the majority's answer. Hiding the earlier answer also changed conformity: Qwen3.5-4B gave in on 89% of questions instead of 8%. In exploratory interventions, injecting the bridge's J-lens direction brought agents back to their original answer only in the two Qwen models. Stated consensus in multi-agent debate can thus overstate agreement. We also report the negative results of our pre-registered program.

Ziang Ni, Peng Zou

Sun Yat-sen University Guangzhou, China

Normative Conformity in Language Models Multi-Agent Debate Reasoning Consistency in Language Models Multi-Agent Consensus Multi-Agent Deliberation

Sep 29, 2026

Multi-agent discussion gains less when dissent is withheld

Multi-agent systems of LLMs add discussion to majority voting and are therefore expected to be more capable. However, empirical reports conflict on whether discussion improves accuracy or leads to an incorrect consensus. Here, we introduce a parsimonious model that explains when discussion improves accuracy and when it ends in an incorrect consensus, built from four behaviors repeatedly observed in LLM agents: (1) withholding dissent, (2) internalizing a stated answer, (3) reconsidering after seeing dissent, and (4) correcting toward the correct answer. The model shows that discussion can overturn an incorrect initial majority only when the withholding rate

c

is below a critical rate

c^* = γ/(γ+ a)

, set by the net correction rate

γ

and the internalization rate

a

. We estimate these rates from conversation logs with a Bayesian method and place LLM teams relative to

c^*

. As the model predicts, the gain from discussion shrinks as withholding rises, across LLMs and on a hidden profile benchmark, HiddenBench, and MedEInst. Instructing agents not to withhold dissent increases this gain. Turning reasoning off also increases the gain, because reasoning raises the internalization rate

a

and keeps agents from reconsidering a minority answer. These findings reconcile the conflicting reports and identify when discussion outperforms majority voting.

Chand Sahil Mansuri, Xin Wang, Mengying Li +4

School of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY, USA · School of Management, Binghamton University, Binghamton, NY, USA · IBM T. J. Watson Research Center, Yorktown Heights, NY, USA

Multi-Agent LLM Systems Opinion Dynamics Multi-Agent Debate Multi-Agent Consensus LLM Agent Reliability Multi-Agent Deliberation

Sep 25, 2026

OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas

Debates amongst agents driven by large language models (LLMs) have demonstrated vast potential in various applications, but when these interactions include humans and take place in high-stakes environments, e.g., in public policy deliberations, they are beset with issues such as sycophancy and a lack of faithful explanations. To tackle these issues, we present OmouAI, an interactive and inclusive deliberation system that uses LLMs in combination with computational argumentation, a field which excels in representing and reasoning within debates. OmouAI allows a human user to deliberate policy claims for real-world challenges with simulated personas, e.g., representing stakeholders, domain experts or devil's advocates, towards reducing sycophancy. Each persona generates its own arguments, and the arguments of all parties form a shared argumentation framework. Users can then contest, add and revise arguments, providing crucial human oversight. Then, arguments are evaluated using deterministic argumentative semantics against external goals, such as the UN Sustainable Development Goals, guaranteeing faithful explanations. The advancement or worsening of the goals thus serve as indicators for the policy recommendations.

Stylianos Loukas Vasileiou, Antonio Rago, William Yeoh +1

New Mexico State University · King’s College London · Washington University in St. Louis +1

Multi-Agent Deliberation Human-in-the-Loop AI Multi-Agent Debate Deliberative Democracy Large Language Model-Based Role-Play Simulation

Sep 24, 2026

DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents

In open-ended problem solving, collaborators often rely on discussion to surface concerns, challenge perspectives, and refine shared work as it evolves. While AI agents are increasingly used as discussion partners, existing multi-agent systems place a heavy burden on users to initiate and carefully orchestrate the discussions. We present DocuTeam, a mixed-initiative multi-agent discussion system in which both users and agents can initiate and steer conversations. Agents monitor document changes to proactively start and redirect discussions as the work evolves, while users can flexibly shape the conversation or adopt agent ideas. In a within-subjects study (N=20), participants using DocuTeam produced outcomes rated significantly more novel, relevant, and specific than with a baseline without any increase in cognitive load. Rather than using agents for one-off idea sourcing, participants engaged in an iterative refinement loop in which document changes prompted agent reactions, which led users to revisit and further develop their work.

Heechan Lee, Juhyeon Choi, Tae Soo Kim +2

School of Computing, KAIST, Daejeon, Republic of Korea · College of Liberal Studies, Seoul National University, Seoul, Republic of Korea · SkillBench, Santa Barbara, CA, USA

Multi-Agent Collaboration Human-AI Interaction Multi-Agent Communication Human-AI Collaboration Mixed-Initiative Interaction Multi-Agent Deliberation

Sep 18, 2026

The Wisdom of Artificial Deliberative Crowds

The aggregation of many lay estimates often outperforms individual expert judgment, a phenomenon known as the wisdom of crowds. While this is usually attributed to the independence of estimates, an even stronger effect arises through deliberation: averaging the consensus estimates of small deliberating groups outperforms the classical wisdom of crowds, with individual judgments themselves also becoming more accurate after deliberation. Whether these improvements transfer to large language models deliberating amongst themselves is unknown. Here we adapt a three-stage deliberation paradigm previously used with human participants for use with large language models from three different families, and test it across four domains of increasing real-world stakes: visual numerical estimation (Study 1), peer review of machine-learning papers (Study 2), detection of hidden malicious behavior by an artificial intelligence agent (Study 3), and sports forecasting against a real prediction market (Study 4). Across domains, deliberation reduced collective error beyond passive aggregation of independent responses, and post-deliberation individual judgments retained this collective gain. Notably, the advantage required model diversity: groups composed of clones of a single model did not benefit from deliberating. These results establish machine deliberation as a general-purpose aggregation mechanism, and point to diversity as an active ingredient.

Federico Barrera-Lemarchand, Mariano Sigman, Joaquin Navajas

Laboratorio de Neurociencia, Escuela de Negocios, Universidad Torcuato Di Tella, Buenos Aires, Argentina · Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Buenos Aires, Argentina

Multi-Agent Deliberation Multi-Agent Consensus Language Model Ensembles Multi-Agent Systems Opinion Dynamics Ensemble Diversity

Sep 7, 2026

From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction

Can LLM agents simulate how a real public would deliberate? For such simulations to be meaningful, agents must reflect the population's opinions, and their views must be shaped by what others say during discussion. We evaluate these requirements across six LLMs using national surveys, controlled deliberation experiments, and a real deliberative poll. Comparing census-grounded Korean personas against national surveys, we find that agents often produce overly concentrated opinions and fail to reliably reproduce demographic differences. During simulated deliberation, agents exchange arguments, respond to one another, and frequently change positions. Yet similar changes occur even when agents cannot see one another's contributions, while simply restating their starting positions sharply reduces movement. We further test whether these limitations persist in a real-world setting, using agents constructed from actual respondents in the 2017 Shin-Kori deliberative poll. Even with real respondent profiles, agents fail to reproduce the panel's initial opinion distribution or how its opinions change across survey waves. Our findings show that generating deliberative discussions, representing public opinion, and reproducing interaction-driven opinion change are distinct capabilities. These results suggest a different potential role for LLM deliberation: surfacing arguments and perspectives, rather than simulating a real public.

Chaemin Jang, Junsik Min, Jaewoo Choi +9

Korea Advanced Institute of Science and Technology (KAIST) · Seoul National University

Opinion Dynamics Human Behavior Simulation Multi-Agent Debate Large Language Model-Based Social Simulation Demographic Bias in Language Models Multi-Agent Deliberation

Sep 3, 2026

Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation

Multi-agent debate (MAD) improves the reasoning capabilities of large language models by having multiple agents iteratively refine their responses through discussion. However, MAD suffers from a critical vulnerability known as shared misconception: when a majority of agents initially converge on an incorrect answer, the debate process tends to amplify rather than correct the error. Existing methods primarily address peer skew but leave the agents' inherently biased concept priors unaddressed. To mitigate this systematic weakness, we propose R

^2

-MAD (Remember and Reweight for Multi-Agent Debate), a framework that equips agents with an experience memory accumulated from past debates. R

^2

-MAD intervenes on both failure modes through two complementary mechanisms: A debate-state-aware retrieval policy dynamically calibrates the concept prior by retrieving relevant historical evidence based on the current consensus level. Then these retrieved experiences provide a basis for estimating per-agent reliability, yielding confidence weights to modulate peer influence. Experiments on various benchmarks show that R

^2

-MAD achieves consistent improvements over existing single-agent and MAD baselines.

Xuanfa Jin, Zhijian Ma, Yongcheng Zeng +3

Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · University College London

AI Agent Reliability Multi-Agent Debate Multi-Agent Consensus Memory-Augmented Language Model Agents Multi-Agent Deliberation

Aug 24, 2026

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

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, Jinhao Shen +3

The Hong Kong Polytechnic University · Sichuan University

Multi-Agent Debate Multi-Agent Deliberation Metacognition in Language Models RL for Language Model Reasoning

Aug 18, 2026

What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation

A common multi-agent design asks agents to report confidence and lets the highest-scoring agent speak next, implicitly using one scalar both to route the conversation and to estimate uncertainty. We audit this confidence-routed broadcast protocol by separating three trace-level questions: whether it selects the right candidate (routing), whether reported confidence behaves like a probability (calibration), and whether the selected agent publicly states the answer that won the turn (commitment). Our primary study covers 4,181 gpt-oss-120b olympiad-math traces; we repeat the audit on a 2-by-2 actor-by-benchmark grid that adds gemma-4-31B-it and a biology multiple-choice benchmark. In the primary cell, confidence discriminates correct from wrong candidates (AUROC 0.72) but is strongly overconfident (79% mean stated confidence versus 52% accuracy). A cross-fitted, tier-stratified isotonic procedure reduces Expected Calibration Error from 0.278 to 0.008 on held-out candidates, but it does not recover missing discrimination: raw AUROC is only 0.537 and 0.440 in the two Gemma cells. Routing is likewise setting-dependent. Fixed routers differ by at most 1.1 percentage points on gpt-oss/math, whereas raw-confidence argmax performs 5.6 and 11.2 points below random-valid selection in the Gemma cells. Commitment is distinct again: in the primary cell, poll and spoken answers diverge in 20.4% of valid pairs, 62.4% of those revisions are fresh generations, and the unconditional correctness shift is -1.7 points; the other three cells instead range from +0.9 to +12.2 points. The transferable lesson is procedural: routing discrimination, probability calibration, and public commitment must be measured separately before raw confidence is used for deployment decisions.

Jingyan Jiang, Huihuo Zheng, Rajeev Thakur +1

Argonne National Laboratory, Lemont, IL 60439, USA

Multi-Agent Deliberation LLM Agent Routing AI Agent Auditing Multi-Agent Systems Confidence Estimation in Language Models Language Model Calibration

Aug 14, 2026

Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages

Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently generated messages and replays the same downstream solver, called the integrator, with each message available or hidden. The replay comparison measures a message's trajectory value: whether making the message available helps or harms subsequent reasoning. Across five mathematics and science benchmarks and two openly available model families, gpt-oss-120b and gemma-4-31B-it, wrong-helpful messages appear in every benchmark-model combination. Among wrong-answer messages that change final correctness, more than four in ten changes are helpful in each model. Controlled repeats show that the number of repeatable message effects is unlikely to arise from replay variation alone (p=0.0002). A focused intervention on repeatable wrong-helpful messages finds that the complete message works best, while retaining its reasoning preserves more success than retaining only its answer; the source of the complete-message advantage remains open. Within the same problem, repeated trajectory-value evidence also identifies a better keep-or-remove choice than answer correctness alone. Answer correctness is therefore informative but does not determine trajectory value. DHD measures this missing property and produces reusable labels for learning when agents should listen.

Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang +7

Argonne National Laboratory, Lemont, IL, USA · University of Houston, Houston, TX, USA · Brookhaven National Laboratory, Upton, NY, USA +1

Multi-Agent Reasoning LLM Agent Evaluation Multi-Agent Communication Multi-Agent Deliberation

Aug 13, 2026

BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs

Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-agent systems, humans typically provide an initial problem, agents deliberate internally, and the system returns a final response. BoardroomAI instead treats the human as a persistent participant who can intervene by challenging assumptions, modifying constraints, changing priorities, introducing evidence, or redirecting the decision process. We operationalize this human--agent coexistence through four components: (i) a typed decision graph representing evidence, assumptions, constraints, claims, objections, alternatives, risks, decisions, semantic dependencies, and specialist responsibility; (ii) an intervention compiler that converts confirmed human actions into explicit graph updates; (iii) dependency-aware propagation that identifies affected subgraphs, preserves unaffected artifacts, and selectively reactivates relevant specialists; and (iv) an evaluation framework measuring intervention impact, repair coverage, preservation, recomputation, and decision validity. Across 600 generated decision-DAG interventions, propagation matched exhaustive impact computation while inspecting only 14.59% of nodes. In a 12-case exploratory pilot, selective repair recomputed 62.11% of canonical nodes, preserved all gold-unaffected nodes, and produced valid updated decisions in six cases while abstaining in the remaining six. These abstentions show that correct intervention routing may still provide insufficient context for synthesis, motivating a decision-sufficient context closure for human-steered multi-agent deliberation. All results are synthetic and prototype-level.

Sanjeev Manivannan

Indian Institute of Technology Madras, Chennai, India

Human-in-the-Loop AI Multi-Agent Systems Human-AI Decision Making Multi-Agent Deliberation

Aug 4, 2026

Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems

Clinical decision support is moving toward committees of language-model agents deliberating on a shared workspace. We ask whether such committees can be gamed by shortcuts, cues a benchmark rewards but a clinician would ignore. Across seven cohorts on six public datasets spanning text (MedQA-USMLE, MedMCQA, MIMIC-CXR reports), imaging (NIH ChestX-ray14, MIMIC-CXR-JPG, CheXpert) and tabular ICU records (SUPPORT2), Gemini committees resist these cues in isolation (flip 5-16%), yet a socially plausible shortcut spreads: when two peers assert the same wrong answer, the holdout under test adopts it in 38% of cases, as does a false "pre-screen" system flag, on both capability tiers. Of three oversight agents, a gate cannot separate adoption from honest agreement (false-positive rate 100%); a same-lineage judge reading only the transcript flags adoption on text (precision 100%, recall 93%) but collapses onto the gate in imaging; a referee that privately re-queries the holdout transfers to imaging (77-88% precision, 13-21% false-positive rate). Tripling a cue's visual salience does not move contagion, whereas a second peer voice raises it by half again. Gaming a hidden rubric is near-silent: only 1/10 text and 1/134 imaging drifters name the rubric they moved toward. What games a committee is social plausibility, and only a referee independent of self-report catches it. Code: https://github.com/criticaldata/benchmaxxing

Sebastián Andrés Cajas Ordóñez, Agastya Munnangi, Aldo Marzullo +13

MIT Critical Data, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States · Georgia State University, Atlanta, Georgia, United States · Politecnico di Milano, Milan, Italy +12

Emergent Behavior in Multi-Agent Systems Multi-Agent LLM Systems Clinical Decision Support LLM Agent Evaluation Multi-Agent Systems AI Agent Safety Benchmarks+2

Aug 2, 2026

Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering

Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Multi-Agent Debate (LMAD), an inference-time protocol that represents agent rationales as nodes, locates their earliest conflict, and restricts debate to the corresponding local segments. Guarded resolution extends a shared committed state so that later conflicts can be addressed without reopening accepted steps. We evaluate LMAD on four multi-hop question-answering benchmarks using ten backbones from four model families. Our method achieves the highest macro-averaged judge accuracy across all ten backbones, outperforming the strongest conventional baseline by up to 7.20 percentage points.

Weijun Gao, Xiang Ding, Haoyang Liu +1

1The Chinese University of Hong Kong · 2Nagoya University · University of Illinois Urbana-Champaign +1

Multi-Hop QA Multi-Agent Debate Multi-Agent Reasoning Multi-Agent Deliberation

Jul 7, 2026

LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability

Deliberation plays a crucial role in collaboration; when humans work together, they naturally engage in communication to align information and reach an agreement. In this paper, we investigate deliberative large language model (LLM) agents under partially observable joint decision-making tasks. We formalize deliberative collaboration as a cooperative joint decision problem with partial and asymmetric observations, and introduce a scalable benchmark that instantiates this problem across multiple task settings and domains in which agents must exchange information through deliberation to reach a joint decision with a shared reward. We then instantiate a reference scaffold and evaluation protocol for deliberative agents and conduct a systematic evaluation of a range of representative LLMs. The results reveal that complex deliberative collaboration tasks continue to challenge state-of-the-art language models. Even with the aid of external mathematical tools, language models may fail in either the deliberation process for aligning information or the complex reasoning process for making the decision. On the other hand, diagnostic analysis reveals that the deliberation process may also provide opportunities for reflection and error correction, sometimes improving performance over centralized baselines. Altogether, our work establishes a foundation for evaluating and improving LLM agents in deliberative collaboration and provides insights into the strengths, limitations, and properties of current LLM-based multi-agent systems.

Chenxu Wang, Yongkun Yang, Boyuan Du +2

Department of Computer Science and Technology, Tsinghua University · Fuzhou University

LLM Agent Evaluation Multi-Agent Collaboration AI Agent Benchmarks Multi-Agent Reasoning Multi-Agent Deliberation

Jul 2, 2026

Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry

Multi-agent systems are increasingly used for forecasting future events, as deliberation among multiple LLMs is believed to improve reasoning and calibration. Yet existing approaches overlook a critical design choice: what information each agent receives. When all agents are given identical evidence, deliberation collapses into herding rather than genuine belief revision, leaving multi-agent systems little better than a single agent. We identify this as a fundamental gap and propose designed information asymmetry to close it: by partitioning evidence into shared public and disjoint private subsets, each agent holds exclusive knowledge that can only reach others through deliberation. We theoretically show that this decomposition reduces inter-agent error correlation, and instantiate it in InfoDelphi, a framework combining relevance-aware evidence routing, rationale-based iterative deliberation, and confidence-weighted aggregation. On PolyGym, a benchmark of 375 binary forecasting questions derived from real-world prediction markets, InfoDelphi outperforms the strongest single-agent and multi-agent baselines by 12--18% in Brier score and 4--8 percentage points in accuracy. More detailed experiments confirm that removing information asymmetry eliminates most deliberation gains, establishing diversity of input as the key enabler of effective multi-agent reasoning.

Yuante Li, Yicheng Tao, Kate Zhang +3

School of Computer Science, Carnegie Mellon University · College of Engineering, Carnegie Mellon University

Probabilistic Forecasting Multi-Agent Debate Multi-Agent Reasoning Multi-Agent Deliberation

Jun 29, 2026

Investigating Multi-Agent Deliberation in Law

Artificial Intelligence is increasingly applied to the field of law, and has the potential to increase access to justice. One particular movement that is gaining traction is that of agentic AI, wherein AI agents, based on Large Language Models (LLMs) can take autonomous actions. In particular, multi-agent approaches in the legal domain remain largely unexplored. In this paper, we investigate multi-agent deliberation methods for legal reasoning tasks using LLMs. We explore multi-agent deliberation (MAD) and introduce two novel multi-agent frameworks inspired by courtroom procedures and legal argumentation. Our experiments on both legal and non-legal benchmarks reveal that multi-agent frameworks achieve comparable overall performance to baseline large language models, but produce significantly distinct answers. Notably, these approaches can successfully solve cases that the baseline fails to address, and vice versa. We conduct a qualitative evaluation and highlight scenarios where multi-agent frameworks outperform monolithic approaches. For example, multi-agent approaches appear better suited for answering questions that require critical thinking from multiple perspectives. Our work positions multi-agent systems as a promising direction for AI in the legal domain, while demonstrating the potential of law-inspired multi-agent approaches for deliberation.

Cor Steging, Ludi van Leeuwen, Tadeusz Zbiegień

Bernoulli Institute of Mathematics, Computer Science and Artificial Intelligence, University of Groningen The Netherlands · Department of Legal Theory, Jagiellonian University Poland

Multi-Agent Systems Multi-Agent Reasoning Multi-Agent Deliberation Legal Reasoning

Jun 28, 2026

Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds

Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and when it should be escalated to human review. We formulate this as budgeted act-or-defer decision making. At each round, the system maps the debate prefix to a low-dimensional state, computes a

k

-nearest-neighbor lower confidence bound on state-conditional correctness using calibration data, and acts only when the bound exceeds a user-specified reliability threshold. The certificate controls wrong actions through the decomposition

β= δ+ α+ \varepsilon_{\mathrm{act}}

, separating calibration failure, residual action risk, and representation gap. The guarantee is conditional, not distribution-free: it relies on a valid local bias envelope and an action-region representation-gap bound, and each assumption is paired with falsification-style diagnostics. Because the same absolute wrong-action budget has different meanings across tasks of different difficulty, we set budgets relative to each task's final-round error using training data only, and evaluate safety by normalized budget usage

\mathrm{WA}/β

. On six benchmarks against nine baselines, the method uses 9--12% of the pre-declared budget on activated datasets, reaching up to 84% automation and 96% acted-on accuracy; on stress-test datasets, it defers rather than forcing unreliable automation. Rather than relying on per-task post-hoc threshold search, the method prospectively converts a user-declared wrong-action budget into an auditable act-or-defer operating point before deployment, under explicitly stated assumptions.

Mengdie Flora Wang, Haochen Xie, Guanghui Wang +2

1AWS Generative AI Innovation Center, USA · General Motors (GM), USA

AI Agent Reliability Multi-Agent LLM Systems Selective Prediction LLM Decision-Making LLM Agent Reliability Multi-Agent Deliberation

Jun 17, 2026

Hidden Anchors in Multi-Agent LLM Deliberation

Multi-agent LLM deliberation, where agents exchange and revise answers over several rounds, is increasingly used to improve reasoning and accuracy, yet how and why it works is rarely modelled. Such deliberation mirrors how humans reach decisions. As social animals we are pulled both by the group, the herd effect that classical opinion-dynamics models such as DeGroot and Friedkin--Johnsen capture, and by our own internal belief, which they do not. We model multi-agent deliberation as a closed-loop dynamical system in which each agent carries a hidden internal belief, its anchor, that continually pulls its opinion regardless of its neighbours. We show this anchor can be recovered from the deliberation alone, and that it explains a behaviour classical consensus rules forbid: an agent's confidence in the correct answer can climb past where any agent started, escaping the space (convexhull) formed by the initial beliefs. Checking whether the recovered anchor also predicts held-out runs (generalizes) gives a simple test for when a model is truly driven bysuch an anchor. Across three open-weight model families this is a spectrum, not all-or-nothing. All anchors' influence are about equally strongly, but they differ in where the anchor sits, and only when it sits far from the initial opinions does deliberation escape the hull and need the full closed-loop model.

Apurba Pokharel, Ram Dantu

Department of CSE University of North Texas 76207, Denton, TX, USA

Opinion Dynamics Multi-Agent Debate Multi-Agent Reasoning Multi-Agent Deliberation

Jun 2, 2026

The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation

Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts and viewpoints needed to interpret an issue. We identify the deliberative illusion: discussion produces (1) factual attrition, the progressive loss of issue-critical facts, alongside (2) stance homogenization, the collapse of diverse positions toward consensus. To measure this process, we introduce DelibTrace, a framework that decomposes each issue into atomic facts, labels issue-critical ones, distributes them across agents, and tracks their survival across discussion rounds. Across ethical and news-based deliberation with three representative LLM families, multi-agent discussion erases up to 72% of issue-critical facts. This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context. These results reveal a sharper risk: agents can agree more while knowing less. We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.

Herun Wan, Jiaying Wu, Minnan Luo +4

Xi’an Jiaotong University · National University of Singapore · Yunnan University +1

Multi-Agent LLM Systems LLM Agent Evaluation Multi-Agent Debate Multi-Agent Consensus Multi-Agent Deliberation

Jun 1, 2026

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation. However, existing multi-agent debate and collaboration frameworks typically adopt fully connected communication, causing the number of messages, token costs, and end-to-end latency to grow approximately quadratically with the number of agents; although fixed sparse topologies reduce overhead, they cannot adapt communication relationships to different task instances or intermediate reasoning states, making them prone either to preserving low-value interactions or to losing critical error-correction information. To address this problem, this paper proposes DySCo (Dynamic Sparse Consensus), a dynamic trust-aware sparse consensus mechanism. In each round of reasoning, DySCo estimates the value of communication edges based on agent reliability, answer divergence, and task relevance, and selects a small number of high-value edges for message exchange under budget constraints; it then aggregates the answers of different agents through dynamic trust weights and terminates the discussion early once consensus stabilizes. This mechanism replaces universal broadcasting with on-demand communication, thereby reducing communication overhead while preserving essential cross-validation information. We further present analyses of communication complexity and consensus stability, and evaluate the performance of DySCo on mathematical reasoning, logical reasoning, and factual question-answering tasks.

Wanshuang Gou, Zihan Liu

Chengdu University

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Debate Multi-Agent Consensus Communication Complexity+3

May 25, 2026

Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?

The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collaborate. We study this mechanism through the lens of Friedkin-Johnsen (FJ) opinion dynamics, a tractable model for analyzing stubbornness, influence, and opinion change in multi-agent systems that captures empirically observed deliberation patterns. We show that the FJ parameters are input-dependent, turning multi-agent deliberation into a mixture of experts. This perspective implies that multi-agent systems can outperform single agents and static ensembles when routing reflects agent competence. Since competence is latent in practice, we analyze how influence is established through observable proxies: agents' self-assessed confidence, their perceived confidence, and initial alignment with other agents' views.

Franka Bause, Jonas Niederle, Martin Pawelczyk +1

CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Faculty of Computer Science, University of Vienna, Vienna, Austria.

Multi-Agent LLM Systems Opinion Dynamics Mixture of Experts Multi-Agent Collaboration Multi-Agent Reasoning Multi-Agent Deliberation

May 24, 2026

DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces, incorrect intermediate reasoning may be adopted and amplified, leading to confident but wrong consensus; multi-round communication also increases token consumption, latency, and inference cost. In this paper, we propose a controlled-communication coordination framework named DarkForest. DarkForest first keeps agents independent, so each agent produces an answer without seeing the others' outputs. It then parses the raw responses into structured candidate records, groups semantically equivalent candidates into clusters, and estimates a calibrated belief distribution over these clusters using agent reliability, confidence, parse quality, support-pattern reliability, and independence corrections. A coordinator receives only policy-permitted evidence from this belief state with controlled communication. Experiments on six reasoning benchmarks show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7% on benchmark metrics, and reduces token consumption by up to

6.5\times

compared with communication-heavy baselines.

Yi Li, Songtao Wei, Dongming Jiang +3

University of Texas at Dallas · Independent Researcher · University of California, Davis

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination LLM Agent Workflow Optimization Agentic Reasoning Multi-Agent Systems+4

May 12, 2026

CHAL: Council of Hierarchical Agentic Language

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 9, 2026

Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design

Multi-agent AI systems need behavioral constitutions, but it is unresolved whether such rules should emerge internally through agent self-governance or be discovered externally through optimization. We present the first controlled comparison of internal deliberation and external evolution across three social environments: a coordination grid-world, an iterated public goods game, and a bilateral trading market. Across 180 simulation runs, evolution significantly outperforms deliberation in collective-action settings (p < 0.01), while neither method improves outcomes in bilateral trading. A multiplier ablation reveals that evolution's advantage inverts when incentives shift: at pool multiplier (m = 0.75) the evolved constitution forces value-destroying cooperation and becomes the worst-performing method. Notably, no deliberation run across thirty trials ever proposed punishment -- the canonical cooperation-sustaining mechanism evolution reliably discovers -- suggesting external optimization wins on peaks while internal self-governance trades peaks for structural responsiveness.

Hershraj Niranjani, Ujwal Kumar, Phan Xuan Tan

Department of EECS, University of California, Berkeley, Berkeley, CA, USA · College of Engineering, Shibaura Institute of Technology, Tokyo, Japan

Evolutionary Optimization Multi-Agent Systems AI Agent Governance Multi-Agent Deliberation Emergent Behavior in Multi-Agent Systems

Apr 29, 2026

Preserving Disagreement: Architectural Heterogeneity and Coherence Validation in Multi-Agent Policy Simulation

Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value perspectives. We present the AI Council, a three-phase deliberation framework, and conduct 120 deliberations across two policy scenarios to test two interventions. First, architectural heterogeneity (assigning a different 7-9B parameter model to each value perspective) significantly reduces first-choice concentration compared to a homogeneous baseline (child welfare: 70.9% to 46.1%, p < 0.001, r = 0.58; housing: 46.0% to 22.9%, p < 0.001, r = 0.50). This contrasts with accuracy-oriented multi-agent debate, where heterogeneity does not reduce convergence, suggesting model diversity operates differently when no objectively correct answer exists. Second, coherence validation (using a frontier model to assess whether each evaluator's reasoning is grounded in its assigned values) reveals a fidelity-diversity tradeoff: on a scenario with a dominant option, it further reduces concentration (46.1% to 40.8%, p = 0.004), but on a scenario with genuinely competitive options, it increases concentration (22.9% to 26.6%, p = 0.96) by amplifying high-coherence evaluators who cluster on one option. This tradeoff may be a general property of multi-agent systems employing quality weighting. We report negative results from three failed Delphi designs, demonstrate that 8B models exhibit binary rather than graded responses to counter-arguments, and propose the trustworthy tension rate as a diagnostic measure of small-model deliberation capabilities.

Ariel Sela

Tel Aviv University

Multi-Agent LLM Systems Multi-Agent Coordination Multi-Agent Systems Multi-Agent Consensus Multi-Agent Reasoning Multi-Agent Deliberation

Apr 9, 2026

From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation

Multi-agent debate improves LLM reasoning, yet agreement among agents is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus-based stopping commits that error to an automated action with no recourse. We introduce Conformal Social Choice, a post-hoc decision layer that converts debate outputs into calibrated act-versus-escalate decisions. Verbalized probability distributions from heterogeneous agents are aggregated via a linear opinion pool and calibrated with split conformal prediction, yielding prediction sets with a marginal coverage guarantee: the correct answer is included with probability

{\geq}\,1{-}α

, without assumptions on individual model calibration. A hierarchical action policy maps singleton sets to autonomous action and larger sets to human escalation. On eight MMLU-Pro domains with three agents (Claude Haiku, DeepSeek-R1, Qwen-3 32B), coverage stays within 1--2 points of the target. The key finding is not that debate becomes more accurate, but that the conformal layer makes its failures actionable: 81.9% of wrong-consensus cases are intercepted at

α{=}0.05

. Because the layer refuses to act on cases where debate is confidently wrong, the remaining conformal singletons reach 90.0--96.8% accuracy (up to 22.1pp above consensus stopping) -- a selection effect, not a reasoning improvement. This safety comes at the cost of automation, but the operating point is user-adjustable via

α

.

Mengdie Flora Wang, Haochen Xie, Guanghui Wang +9

AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China

LLM Agent Safety Selective Prediction Multi-Agent Deliberation Conformal Prediction Multi-Agent Debate Multi-Agent Consensus