Multi-Agent Consensus

Follow this topic Ask about this topic

Momentum

16 papers in the last four weeks, up 300% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 75

Oct 5, 2026cs.RO

Entropy-Gated Belief Coordination for Decentralized Multi-Agent Search Under Intermittent Communication

We study decentralized multi-agent target search where homogeneous agents communicate intermittently at Poisson-distributed times. Standard unconditional belief fusion wastes communication opportunities by synchronizing agents during high-entropy exploration, when diverse independent beliefs provide better coverage than a premature consensus. We introduce \emph{entropy-gated belief coordination}, in which agents skip fusion while their collective entropy ratio exceeds a threshold~

θ

and merge only during exploitation, consistent with the bifurcation structure of nonlinear opinion dynamics and the submodular structure of the per-step information gain objective. We further derive

\Istep(α,β)

, the expected mutual information per observation step between two agents' binary sensors, as an interpretable, communication-free measure of sensor informativeness that motivates the gating design and guides system-level analysis. Experiments across 103{,}680 trials (nine grid sizes up to

100{\times}100

, Poisson communication timing, four target movement patterns) show that the Entropy-Gated Trust-Decay Planner (\textsc{EG-TDP}), which adds a detection-probability planner switch in exploitation mode, achieves mean belief quality

\bar{Q}=0.300

(mean belief mass at the true target cell, averaged across all trials and steps), a

58.9\%

gain over arithmetic mean and a

37.4\%

gain over visit-weighted fusion. On representative configurations, EG-TDP also outperforms a joint-Bayesian reference that uses all agents'~observations at every step, despite operating under random intermittent contact only.

Mohamed Abdelnaby, Kevin Leahy

Department of Robotics Engineering, Worcester Polytechnic Institute

Belief-Space Planning Multi-Agent Coordination Multi-Agent Systems Multi-Agent Consensus Multi-Agent Communication

Oct 2, 2026cs.CL

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

Oct 1, 2026cs.AI

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

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

Ionel Eduard Stan, Paolo Napoletano

Department of Informatics, Systems and Communication (DISCo), University of Milano–Bicocca, Milan, Italy

Language Model Calibration Computational Argumentation Adversarial Robustness of Language Models Multi-Agent Consensus LLM Agent Reliability

Sep 30, 2026cs.MA

Consensus and Factual Dynamics in Large Populations of Interacting Language Models

Large Language Model (LLM) agents are increasingly deployed as populations of interacting entities, in which consensus --agreement on a shared answer-- emerges as a collective, unengineered behaviour. Prior work on LLM consensus shows that agents can cross-verify their answers and converge towards more factual responses, treating agreement as a proxy for correctness. However, these studies usually fix a single interaction structure, leaving open how consensus depends on how agents interact. We address this gap by introducing RHEON, a physics-inspired framework that recasts a population drawn from a single frozen model as an evolving

O(n)

spin system on a ladder of interaction geometries of increasing effective dimension --from a 1D ring to a full-coupling mean-field graph-- with the sampling temperature

T

as the tunable source of thermal disorder, evolved through a Glauber-like asynchronous dynamics. Sweeping RHEON across

432

configurations of prompt, population size, communication topology, and sampling temperature yields Eraclitus-4.7M, a tagged evolutionary corpus of

4.7

million responses. We find that agents reach their strongest consensus gain within the first few update sweeps and that increasing the number of neighbours per agent accelerates convergence on average. We further show that whether a configuration settles on factually correct or hallucinated consensus is not predictable from its initial state alone, and that the hallucination-minimising temperature depends on how the agents are coupled, so the common near-greedy default is not automatically the safest. Finally, semantic agreement correlates positively with factual convergence, and interaction strengthens the association, yet never enough for unanimity to certify correctness.

Emanuele Ricco, Elia Onofri, Vincenzo Sammartino +1

Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST) Thuwal 23955, Saudi Arabia · Dipartimento di Informatica, Universit`a di Pisa Pisa, Italy

Hallucination in Language Models Multi-Agent Consensus Multi-Agent LLMs

Sep 29, 2026physics.soc-ph

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

Sep 28, 2026cs.MA

Bregman Consensus

Consider a community of agents who are seeking consensus on a set of parameters. The agents agree to use the same Bregman-type divergence to quantify disagreement between their individual estimates of the parameters but have varying confidence in each other's abilities. Each agent is happy to revise their estimate by moving to the weighted barycenter of all individual estimates with higher weights applied to more trusted agents. We show that such revisions naturally lead to an iterative algorithm which converges to a unique consensus estimate of the parameters. Furthermore, since the consensus estimate is itself a barycenter with computable weights, the group emerges as a collective super-agent with a well-formed opinion regarding the ability of each individual agent.

Andrei N. Soklakov

Functional Bregman Divergences Multi-Agent Consensus

Sep 27, 2026cs.CL

LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems

Large language models (LLMs) are increasingly deployed in multi-agent settings, where agents observe and influence one another, making social influence a key dimension of AI behavior and safety. We investigate whether LLMs' responses depend on the social identity of other agents, beyond the effect of their consensus. We construct judgment tasks with a single correct answer, and place models in a multi-agent setting where they receive incorrect answers from other agents whose social identities (AI or human, model family, or an arbitrary minimal group) are either shared with or distinct from their own. Across 12 open-weights models and nine tasks, we find a bidirectional effect of group identity on conformity to incorrect answers: in-group consensus increases conformity (in-group favoritism), whereas out-group consensus decreases it (out-group divergence). Unlike humans, for whom one ally breaking the consensus sharply reduces conformity, models are unmoved by an ally from the majority's group. Worse, a correct ally from the opposing group intensifies this bidirectional effect. Chain-of-Thought reasoning suppresses most of these effects, yet an in-group ally still reduces conformity to an incorrect out-group majority. Labeling peers as safety-aligned shifts overall conformity but leaves in-group favoritism and out-group divergence intact. These results show that group identity shapes how LLMs aggregate information across agents, independently of its correctness, and identify a manipulation surface for multi-agent AI systems.

Liron Soffer, Ravid Shwartz-Ziv, Chen Shani

Tel-Aviv University · New York University

Normative Conformity in Language Models Social Bias in Language Models Belief Updating in LLMs Multi-Agent Consensus Multi-Agent LLMs

Sep 23, 2026cs.LG

ZO-COSMO: Index-Free One-Hop Mixing for Decentralized Zeroth-Order Optimization

Sparse communication in decentralized zeroth-order learning requires compatible peer-state coordinates. We characterize this one-hop condition and develop \textsf{ZO-COSMO}, coupling two-query estimation with average-preserving masked consensus using

q

values per active link. Global supports serve all-neighbor mixing; matching updates require agreement only within each pair. We derive a sharp contraction-per-scalar bound within the matching class and convergence guarantees for the core and sparse-momentum updates. At fixed matching, exact moment identities characterize how shared directions preserve gradient-heterogeneity cancellation and redistribute estimation error and disagreement. Mechanism experiments cover unequal curvatures, noise, and sparse momentum. Further tests span

64

synthetic agents and eight logical Qwen LoRA workers. At matched payload budgets, Qwen2-7B QNLI gains

3.65

accuracy points over explicit-index Rand-

k

; edge-local updates gain

3.42

and

2.53

points over all-neighbor mixing on eight-worker complete and ring graphs. A matched-first-step ablation gives a

3.92

-point momentum benefit. Seed-aware and same-matching controls distinguish encoding, scheduling, and query correlation.

Shengjun Zhang, Tingyi Liu, Heng Zhang +1

School of Artificial Intelligence, Hubei University, Wuhan, China · School of Economics and Management, Wuhan University, Wuhan, China · School of Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China +1

Communication-Efficient Distributed Training Multi-Agent Consensus Decentralized Optimization

Sep 22, 2026cs.MA

Calibration Is Not Verification: Falsifiability-Aware Conformal Routing for Mixture-of-Agents

Multi-agent language systems often treat agreement as evidence, yet heterogeneous agents can jointly repeat an unsupported claim or omit a correct specialist fact. We introduce C-MoA, an agreement-based conformal filter that turns inter-agent semantic support into a claim-level nonconformity score and calibrates a retention threshold at the example level, giving distribution-free within-domain factuality control for heterogeneous Mixture-of-Agents. C-MoA is effective: it nearly doubles retained-claim precision on long-form generation (from 0.41 to 0.75), certifies a human-labelled medical set, and transfers across domains without recalibration; its one failure mode is short-form answering, where consensus is cheap and the score is left near chance. We then ask whether counterfactual falsifiability can push past consensus, and introduce CONTRA-MoA, which adds a blinded near-miss tournament, leave-one-agent-out stability, and availability-aware fusion. This extension helps only where the verifier holds domain knowledge, dropping half of the false medical claims at 0.940 precision, whereas with a memory-only judge the added signals are near chance (AUC 0.531 and 0.511) and naive max fusion degrades the working agreement signal from 0.687 to 0.652. The message is twofold: agreement-based conformal calibration delivers reliable, transferable factuality control, while moving beyond consensus requires a knowledgeable verifier, availability-aware signals, and robust fusion.

Nada Rahali, Zijia Wang, Zhisong Liu

LUT University, Finland · Dell Technologies, United Kingdom · Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom

Factual Consistency Evaluation Conformal Prediction LLM Agent Verification Multi-Agent Consensus

Sep 21, 2026cs.RO

AC-DC: Adaptive Communication for Scalable Dynamic Average Consensus in Multi-Robot Ergodic Search

We study scalable peer-to-peer dynamic average consensus (DC) for multi-robot systems under finite-range, finite-rate, and interference-constrained communication. We introduce Adaptive Communication for Dynamic Average Consensus (AC-DC), which jointly adapts Who communicates with whom, When, and over What parts of the consensus state, using local inputs and successfully received neighbor information. Each robot's consensus state estimates the current average of the robots' local inputs. AC-DC updates these estimates as local inputs change and averages the values exchanged between robot pairs. In AC-DC, robot pairs update without waiting for every robot to complete a communication round, and the selected-state messages carry consensus state coordinates independent of team size for a fixed state representation. We apply AC-DC to dynamic-priority multi-robot ergodic search: one consensus stream estimates team visitation for motion coordination, while the other fuses regional measurement information to update uncertainty maps and search targets. Across twelve settings with up to 80 robots and 20 paired trials per setting, AC-DC has the lowest mean (i) normalized covariance-trace area under the curve (AUC) and (ii) attempted modeled communication payload among the compared decentralized methods. Averaged across settings, AC-DC achieves paired AUC reductions of 27.5% relative to state-of-the-art baselines, with 8.7x less communication traffic. As the number of robots increases, we observe that AC-DC's communication payload approaches that of the ideal centralized baseline (one ground compute-station communicating directly with all robots): with 120 robots in a fixed 600 x 600 m scaling test, AC-DC uses 19.3 MB versus 19.2 MB for the ideal centralized baseline, while remaining peer-to-peer.

Robin Inho Kee, Begum Cannataro, Vasileios Tzoumas

Department of Robotics, University of Michigan, Ann Arbor, MI, USA · Draper Scholar with the Charles Stark Draper Laboratory, Cambridge, MA, USA · Charles Stark Draper Laboratory, Cambridge, MA, USA +1

Multi-Robot Coordination Multi-Agent Consensus Multi-Agent Communication

Sep 17, 2026cs.AI

Language-model groups overstate consensus when replaying human deliberation on a reasoning task

Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We replayed 100 held-out human Wason groups with matched large language model (LLM) agent groups, seeding one belief-anchored agent per participant's pre-discussion answer and scoring agents and people with the same code. Across human scoring definitions, estimates ranged from 24.0% to 57.0%; about one fifth of participants never posted, whereas agents almost always did. Agent groups remained more consensual in two post-unblinding sensitivity analyses: the submit-based comparison (n = 98) yielded gaps of 34.0 and 43.9 percentage points for chat and reasoning modes, and the participation-matched comparison (n = 45) yielded gaps of 34.1 and 44.4 points. These complementary routes reduced different measurement asymmetries yet converged within 0.5 percentage points. The gap persisted without early stopping and under a reparameterization removing the memorizable answer; reasoning-mode groups then agreed nearly unanimously, mostly on incorrect answers. Simulated consensus did not track collective accuracy, and belief-anchored agent groups were biased estimators of the human group-outcome distribution in this setting. These analyses provide a scoring-explicit basis for assessing simulated-group estimates of human deliberative outcomes.

Tengfei Shao

Global Education Center, Waseda University, Tokyo, Japan

Multi-Agent LLM Systems LLM Agent Evaluation Multi-Agent Consensus

Sep 15, 2026cs.MA

Multi-Agent Learning with Cooperation-Driven Optimization Dynamics

Multilayer Artificial Neural Networks trained via backpropagation are the basic blocks of many, more complex, classification algorithms. Their strength lies in the possibility of realizing, with arbitrary precision, any function. This result comes at the cost of the large number of involved parameters to be optimized. In this work, we propose a mechanism for cooperation, i.e., information exchange among several artificial neural networks, with the goal of reducing model complexity while maintaining performance. More precisely, we consider several "small" agents, i.e., containing fewer parameters than a reference "large" one, that during training share their predictions by incorporating this information into the loss function and thus directly influence weight updates. We consider several strategies for implementing cooperation, e.g., the voter model, majority model, and weighted average model based on an agent's confidence in its prediction. We numerically compare the accuracy of those strategies on several standard benchmarks. Our results support the claim that several small agents can outperform a single large model on a given classification task; the shared signals affect each agent's optimization algorithm by modulating both the descent direction and the step size, converging toward a global consensus. The proposed proof-of-concept significantly reduces the number of parameters to be trained while preserving comparable performance, thereby limiting computational resource usage.

Jarod Ketcha Kouakep, Sreyvi UANN, Timoteo Carletti

Department of Mathematics and Namur Institute for Complex Systems, naXys, University of Namur, Belgium · Department of Applied Mathematics and Statistics, Institute of Technology of Cambodia, Phnom Penh, Cambodia.

Multilayer Perceptrons Neural Network Optimization Multi-Agent Collaboration Multi-Agent Consensus Neural Network Compression

Sep 13, 2026cs.CY

A latent dimension of Condorcet's jury theorem for multiple AI advisers

When the same question is asked of multiple AI advisers, as in self-consistency and LLM-as-a-judge panels, Condorcet's jury theorem predicts that adding independent, competent advisers makes the majority more reliable. The theorem, however, has a latent dimension when viewed from the user's vantage: adding advisers also makes disagreement more visible. A binomial model reveals that this ``visible dissent'' becomes nearly inevitable as the number of advisers grows, and that reliability and disagreement approach certainty at rates that cross at an adviser accuracy of 4/5 (0.8); below it, visible dissent eventually becomes more likely than a correct majority. Even ideal panels of independent and competent advisers can be correct in aggregate but appear divided; such disagreement does not by itself indicate aggregation failure. The way advisers split also provides a common basis for predictive multiplicity, reconciliation load, and reliance miscalibration. These results separate aggregation from disclosure and turn the latter into testable questions about how disagreement should be presented and interpreted.

Kazutoshi Sasahara, Aoi Naito, Ryo Fujie

Institute of Science Tokyo, Tokyo, Japan · Carnegie Mellon University, Pittsburgh, PA, USA

Social Choice Theory Multi-Agent Consensus Majority Voting

Sep 12, 2026cs.AI

When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making

When multiple LLM agents yield conflicting answers, the decision-making process dictates whether agent diversity improves performance or merely compounds shared errors. Existing collective decision-making methods, including voting, electoral rules, and LLM judges, rely on forward reasoning: they map evidence to labels in one direction. Although these methods can combine diverse forward traces, they still aggregate estimates that share this evidence-to-label factorization and can inherit correlated errors within the forward pool. We therefore construct a reverse posterior for each instance through Bayesian backward reasoning from an explicit likelihood. The forward and reverse posteriors provide differently factorized approximations of the underlying posterior. Because estimates from different factorizations may tend to share the same error less often, we use Jensen-Shannon divergence to rank agents by cross-path consistency. This cross-path consistency signal underlies three strategies: hard selection (MinJS), soft reweighting (FwdJS), and log-linear fusion (LogLin). Evaluated on DDXPlus across five LLM backbones, our proposed strategies show consistent improvements: MinJS outperforms random selection across all backbones, FwdJS generally improves over the strongest baseline, and LogLin achieves the best performance among the evaluated methods, with its largest gains on the subset where the agents disagree. Despite its weaker standalone accuracy, the reverse posterior serves as a more useful anchor than forward-only alternatives, providing complementary information for collective decision-making. When labeled data are available, a lightweight two-stage calibration can further refine the reverse anchor and improve aggregation performance.

Ken Chen, Wei Wang, Sachith Seneviratne +2

Department of Mechanical Engineering, The University of Melbourne, Melbourne, Australia · Department of Mechanical Engineering, Sri Lanka Institute of Information Technology, Sri Lanka

Multi-Agent LLM Systems Bayesian Inference LLM Decision-Making Multi-Agent Consensus

Sep 8, 2026eess.SY

Networked Admissibility-Preserving Control for Directed Safe Coordination

This paper addresses safety-critical coordination for scalar agents whose distributed commands are implemented through constrained physical-input dynamics. Agents communicate over a fixed weighted digraph with a directed spanning tree, while their outputs must remain inside a common moving safety corridor and their realized inputs must satisfy heterogeneous asymmetric bounds. We propose a networked Admissibility-Preserving Control (APC) architecture in which an Admissibility-Preserving Input Realization (APIR) governs physical inputs and a logarithmic barrier coordinate represents the safety corridor. The synthesis yields an exact cascade in which exponentially decaying realization errors drive nonsymmetric consensus dynamics. For every compatible compact initial set, the closed-loop system admits a unique complete solution, renders the moving corridor and actuator intervals forward invariant with uniform margins, keeps commands bounded, and achieves exponential consensus. We derive direction-specific sufficient conditions under which positive and negative control demands remain within their corresponding actuator limits. The analysis yields a closed-form barrier-coordinate limit determined by the left Perron vector and initial APIR mismatch. Under strong connectivity and the stated gain and compatibility conditions, partial pinning propagates a constant barrier reference from a nonempty informed subset and assigns the induced safety corridor trajectory. A non-weight-balanced example illustrates the directional certificate and predicted collective motion.

Abhinav Sinha, Lohitvel Gopikannan, Shashi Ranjan Kumar

GALACxIS Lab, Department of Aerospace Engineering, University of Cincinnati, Cincinnati, OH 45221, USA · Intelligent Systems and Control (ISaC) Lab, Department of Aerospace Engineering, Indian Institute of Technology Bombay, Mumbai 400076, India

Safety-Critical Control Control Barrier Functions Multi-Agent Consensus

Sep 8, 2026cs.RO

A Distributed Consensus Particle Filter for Target Tracking using Autonomous Surface Vessels

Maritime target tracking over large distances often requires multi-agent teams without centralized coordination, and intermittent communication. Each agent must maintain an independent estimate that can take advantage of opportunistic communications availability when possible. This can lead to overly confident local estimates in the absence of external data. In this work, we propose an augmentation to a classical particle filter implementation that accounts for this potential source of error by forcing particles to spread strategically in the absence of informative updates from other sensor nodes. We demonstrate our method using Unmanned Surface Vessels (USVs) on a lake, and show that our augmentations do not deteriorate nominal performance, and provide an advantage in some specific edge cases.

Carter Noh, Kyle Crandall, Connor Yates +1

1Brigham Young University · 2US Naval Research Lab, Code 5534

Particle Filtering Multi-Agent Consensus

Sep 7, 2026cs.AI

PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations

Multi-agent federations need governance that answers three questions under adversarial conditions: who participated (identity), did they conform (enforcement), and who decides (authority). A separate question is whether the verification machinery that polices a federation's outputs can also steer a generate-and-test loop toward better answers. Part I. PRIMA introduced prime-power agent identity and a consensus token whose factorization indexes participation, but assumed honest agents. We present PRIMUS, which couples prime-power identity with BLS aggregate signatures (PIAC), derives a safe-kill threshold that reduces false-positive agent termination from 80% to 0.00% under 10% channel noise, gives the closed-form economic boundary where singleton governance outperforms Byzantine quorum (

γ^* \approx 9f

, verified flat across n = 50 to 10,000), and specifies VRF succession with lease and fencing that makes safety unconditional under partial synchrony. Five problems are identified as provably unfixable within the model and stated as scope boundaries. Part II. A verifier is not a solver. We ask whether PRIMA's binary artifact-fidelity verdict can be converted into a graded fitness signal, and measure the conversion on binary covering codes. Calibration against injected fault burden is strong (

ρ

= 0.676 deterministic, 0.819 full); against real LLM-generated candidates the same scores fall to 0.158 and 0.406, roughly a quarter of the calibration value (the same-designer confound, measured). As a pre-filter it beats a random-score control convincingly and a binary gate narrowly. Under 400 iterations of explicit optimization it was not gamed, but only because the objective saturated after one honest answer. A cross-family judge preserves the burden-ordering signal while destroying individual judgments. No covering-code record resulted. Measured program cost: USD 164.78.

Sasank Annapureddy, Anjaneya Prasad Thamatani

LLM Agent Verification Multi-Agent Consensus AI Agent Governance Multi-Agent System Security

Sep 3, 2026cs.CL

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

Sep 1, 2026cs.MA

ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research

Multi-agent systems have shown strong performance in domains with reliable verifiers such as coding, where multi-parallel candidate generation selected by a verifier is effective. However, such pipelines would not generalize to open-ended, long-horizon research tasks without a verifier. While majority voting or self-consistency is often used to reach consensus as a proxy verifier, parallel agents repeatedly explore the same evidence, while access to peers' partial findings cause search to converge on an early candidate before alternatives are tested. We present ArcticSwarm, a multi-agent research architecture that separates evidence gathering from evidence integration. Subagents publish findings to a shared bulletin board, while gated isolation lets selected search tasks maintain their own prior, preventing early consensus. Structured review at three commitment boundaries enforce only confident candidates to be propagated. As a result, ArcticSwarm reaches 82.6% on the full BrowseComp-Plus set with the open-weight Qwen 3.5-27B model, compared with 78.8% without gated isolation and 74.5% additionally with structured review disabled, outperforming aligned baseline MiroFlow runs (70.6%). Extending to live-web BrowseComp, ArcticSwarm reaches 73.6% with GPT-5, which is well above the reported provider system (54.9%) and MiroFlow (63.4%). Overall, the results show that restricting peer reads during evidence gathering and strengthening commitment boundaries before a hypothesis is shared can broaden search and improve long-horizon multi-agent deep research.

Soyoung Yoon, Boyi Liu, Yite Wang +6

Seoul National University · Snowflake AI Research

Deep Research Agents Multi-Agent Collaboration Multi-Agent Consensus Multi-Agent Communication

Aug 17, 2026cs.AI

Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents

AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii) agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI agents, like that of other complex systems, follows compact and predictive dynamical laws.

Batu El, Jinhee Paeng, Fatih Dinc +7

Stanford University · UC Santa Barbara

Multi-Agent LLM Systems Opinion Dynamics Multi-Agent Consensus Multi-Agent Communication Emergent Behavior in Multi-Agent Systems

Aug 13, 2026eess.SP

Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks

6G networks will not be serving as communication infrastructures only; rather, they are expected to evolve into intelligent systems, where thousands of autonomous artificial intelligence (AI) agents are interconnected. The agents are deployed across a wide range of platforms including low Earth orbit (LEO) satellites, high-altitude platforms (HAPs), unmanned aerial vehicles (UAVs), edge servers, and terrestrial devices. These agents continuously observe their environment and exchange information. Semantic communication provides an efficient mechanism for exchanging meaningful information instead of raw data. However, its effectiveness depends on the communicating agents having sufficiently aligned beliefs to correctly interpret and decode the transmitted messages. This assumption becomes difficult to satisfy in the 6G network where heterogeneous AI models operate under diverse computational constraints and continuously acquire different knowledge from their local environments. This article presents a heterogeneity-aware belief synchronization framework for 6G AI-native networks. It uses latent translation models deployed on multi-access edge computing (MEC) servers. These models translate belief updates from one agent to agent-specific knowledge without requiring joint training and a homogeneous architecture of models. By exchanging compact belief updates through a latent translation model only when necessary, the framework preserves privacy, reduces synchronization cost, and minimizes local knowledge drift. We validate the framework through a case study on a multi-layered terrestrial/non-terrestrial network. Results demonstrate that it maintains low synchronization cost, measured by the number of parameters transmitted, and low belief alignment error across the heterogeneous agents in the case study.

Muhammad Hannan Akram, Muhammad Abubakar Rashid, Wassi Haider Kabir +3

School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad 44000, Pakistan · Department of Electronic Engineering, Kyung Hee University, Yongin 17104, South Korea · CONNECT Centre and the Department of Computer Science, Munster Technological University, Ireland

6G Networks Semantic Communication Multi-Agent Consensus Multi-Agent Communication

Aug 6, 2026cs.MA

Certifying Collective Reasoning in Multi-Agent Systems via Koopman Spectral Analysis

Orchestrated collectives of large language model (LLM) agents that debate and vote are an emerging form of computational intelligence: the intelligent behaviour resides in the \emph{interaction}, not in any single agent. They improve task accuracy, yet remain black boxes at the system level: there is no principled test of convergence, no bound on the rounds needed, and no faithful account of what drove a decision. This paper develops a novel framework based on Koopman operator theory and validates its theoretical guarantees on multi-agent consensus dynamics. Treating the collective as one nonlinear dynamical system on a communication graph, we read its essential behaviour off the spectrum of its Koopman transfer operator, an exact linear representation of the nonlinear dynamics estimated from interaction traces. The spectrum yields three machine-checkable certificates: the sub-dominant eigenvalue

λ_2

fixes the intrinsic timescale of reasoning and yields a convergence deadline computable \emph{before} the debate runs; its eigenvector names the coherent factions the collective reasons in, and

|λ_2|

certifies when that explanation is valid; and the leading spectral coordinates form a compressed, auditable message basis. On an attention-consensus model, the deadline tracks observed convergence with log--log correlation

0.93

and bounds it in 96% of 24 configurations; attribution is exact whenever the spectrum certifies metastability; eight of 32 coordinates preserve the decision at 99.7% fidelity; and a certificate learned from 15 debates held on 60/60 held-out debates. The study runs in minutes on a CPU, making spectral certification a practical layer for trustworthy collective reasoning.

Nuzhat Khan, Indrakshi Dey

Universiti Teknologi Malaysia, Johor Bahru, Malaysia · Department of Computing and Mathematics, South East Technological University, Waterford, Ireland

Multi-Agent Debate Multi-Agent Consensus Multi-Agent Reasoning Emergent Behavior in Multi-Agent Systems

Aug 4, 2026cs.AI

When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Diagnostic for Machine Collectives

Collective intelligence research treats disagreement as evidence of epistemic diversity: if agents express different views, the group should retain capacity to revise. In LLM collectives this proxy can break: agents can produce diverse-looking arguments while preserving the same conclusion. We operationalize dispersion-revision coupling: the degree to which an intervention that verifiably increases the dispersion of a collective's outputs in embedding space is accompanied by genuine revision of its epistemic stance rather than premise-preserving reformulation. The diagnostic is black-box: it operates on generated text alone and makes no claims about the internal representations of the generating models. Two channels are measured independently: an output channel, the Coherence Index (CI), verifies that the intervention changed output dispersion; an epistemic channel, per-turn stance annotation, measures whether the collective revised. We propose CI with the Meta-Predictive Clarity System (MPCS), which inserts a Re-Differentiation Protocol (RDP) when outputs over-converge, as a reusable method for estimating this coupling regime. We evaluate five-agent collectives from two configurations (gpt-4o-mini and gemini-2.5-flash; 310 paired episodes per condition). On gpt-4o-mini, conditional dissent improves false-premise recovery by +17.7 points (p<1e-6) while static persona diversity harms recovery (-8.1, p=.007). On gemini-2.5-flash, the same intervention at a comparable budget yields no gain (26.1% vs 27.1%, p=.84) despite a verified dispersion drop; the two treatment effects differ from each other (z=3.79, p<.001). Mechanism tagging shows Gemini preserves the false premise via intra-framework dissent: 94% of tagged post-RDP responses reformulate rather than concede (vs 24% on GPT). We recommend reporting per-intervention stance shift and premise-preservation rate alongside accuracy.

Molood Arman

Independent Researcher Lyon, France

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

Aug 4, 2026cs.MA

When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems

LLM-based multi-agent systems promise effective collaborative reasoning, but communication may amplify local errors into collective risks, and while existing evaluations emphasize final outcomes, they leave the reliability and propagation dynamics of distributed information aggregation unclear, so we introduce ForesightSafety-TIDE, a controlled evaluation framework that strictly pairs all-honest collaboration with controlled deception by a key evidence holder and analyzes the aggregation process through multi-stage voting, testimony adoption, and evidence-root lineage propagation, and using 120 five-agent object-movement environments where partial observations jointly determine a unique endpoint, we evaluate 3 homogeneous LLM-based multi-agent systems, and across these paired conditions, aggregate truth recovery falls from 72.50% to 14.17%, with significant declines for every system, while process tracing and exit ablations show that a single false testimony is adopted more readily than truthful testimony, propagates to higher orders, and persists through honest agents after the deceiver exits, and observers without first-hand evidence suppress incorrect consensus but do not improve truth recovery, so together, these findings reveal both the fragility of distributed fact recovery and its underlying mechanism: false evidence gains collective influence through its adoption and continued propagation by other agents after entering communication.

Chenfei Yan, Zeyang Yue, Feifei Zhao +6

Institute of Automation, Chinese Academy of Sciences · Beijing Institute of AI Safety and Governance · School of Artificial Intelligence, Beihang University +3

AI Agent Evaluation Multi-Agent Systems Multi-Agent Consensus Multi-Agent Communication LLM Agent Reliability

Aug 4, 2026cs.CL

Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems

Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create implicit social expectations: agents may be expected to trust, challenge, defer to, or collaborate with peers. We study the effects of making inter-agent relation semantics explicit. We use a minimal signed-network formulation of relational priors and inject natural-language renderings into agent system prompts while holding the task protocol fixed. Across a commons-governance simulation and multi-agent debate, relational priors primarily act as convergence pressure: increasing relational positivity tends to make agents coordinate or agree more readily. This pressure can help when utility rewards behavioral alignment, as in sustainable resource governance and subjective consensus. It does not, however, reliably improve accuracy. In objective QA debates, higher positivity can increase agreement even when correctness-conditioned agreement does not improve and may decline in some settings. Effects vary by model backbone, relation type, and topology; explicit neutrality is not equivalent to omitting relational framing. We argue that relational priors should not be a default add-on for LLM-MAS. Their safer use is diagnostic and task-specific: compare against a no-prior baseline, monitor correctness-conditioned metrics when truth matters, and omit the relational layer when validation does not justify it.

Ming Shen, Chao Shang, Sadat Shahriar +4

Arizona State University · Amazon Web Services

Multi-Agent LLM Systems Multi-Agent Coordination Multi-Agent Systems Multi-Agent Consensus

Aug 3, 2026cs.MA

Emergence of Biased Consensus in Multi-Agent LLM Debates

Multi-agent LLM debates achieve strong performance on decision-making tasks as well as problem-solving benchmarks, yet their safety and fairness risks remain poorly understood. Notably, interaction can amplify the biases of single LLMs, raising concerns for real-world deployment. We identify the emergence of collective (often biased) norms in multi-agent LLM debates and show that noise (e.g., LLM sampling temperature) is a key driver. To explain this, we propose an analytical framework drawing on physics-inspired theoretical models of social dynamics. We predict a phase transition to collective bias when conformity surpasses a critical threshold given the LLMs' initial bias and debate noise. We test the theoretical predictions through controlled experiments and observe a finite-size crossover consistent with an underlying phase transition. We further find that agent heterogeneity suppresses emergence by smoothing (rounding) this transition. Finally, we show that these insights generalize to realistic decision-making tasks, including investment decisions and LLM-as-a-judge evaluation.

Maya Okawa

CBS-NTT Program in Physics of Intelligence, Harvard University · Physics of Artificial Intelligence Group, NTT Research, Inc.

Opinion Dynamics Social Bias in Language Models Multi-Agent Debate Multi-Agent Systems Multi-Agent Consensus Emergent Behavior in Multi-Agent Systems

Aug 3, 2026physics.soc-ph

Microscopic dynamics of consensus formation in multi-agent LLM Naming Games

Decentralized populations of Large Language Model (LLM) agents can spontaneously reach consensus on shared conventions, yet the microscopic mechanisms by which their internal stochasticity shapes macroscopic ordering remain unexplored. We study a minimal LLM Naming Game in which the listener's decision is a single-token LLM call at decoding temperature

T

, replacing the inventory check of the deterministic Naming Game. Each interaction decomposes into an in-inventory and an out-inventory channel with conditional rates

π(T)\!\equiv\!P(\text{YES}\mid w\in P_j)

and

φ(T)\!\equiv\!P(\text{YES}\mid w\notin P_j)

, whose balance controls an ordering-disordering drift. A mean-field theory of the two-rate dynamics yields an analytical ordering condition that generalizes the consensus threshold of the stochastic Naming Game to a critical line in the

(π,φ)

plane. Across three open-weight architectures, consensus is always reached, but through three distinct listener regimes: permissive (repaint-noise dominated), near-deterministic, and conservative (missed-collapse dominated). The effective finite-size exponent

β(T)

in

t_{\rm conv}\!\sim\!N^β

shifts with temperature, and the temperature-sensitivity

α

in

t_c\!\sim\!e^{αT}

ranges from

{\approx}\,0.67

to

{\approx}\,0

across architectures. Decoding temperature thus emerges as an architecture-dependent control parameter for decentralized LLM populations, quantitatively characterized by the statistical-physics toolkit.

Cristiano De Nobili, Vijayasri Iyer, Alessandro Codello +1

Critiqality, Via Pinturicchio 21, 20133, Milan, Italy · Independent Researcher · DSMN, Ca’ Foscari University of Venice, Via Torino 155, 30172 Venice, Italy +3

Multi-Agent Consensus Multi-Agent LLMs

Aug 2, 2026eess.SY

Resilient Consensus-Based Target Tracking under False Data Injection Attacks in Multi-Agent Networks

Distributed target tracking in multi-agent networks plays a critical role in cooperative sensing and autonomous navigation. However, it faces significant challenges in highly dynamic and adversarial setups. This study aims to enhance the resilience of decentralized target tracking algorithms against measurement faults and cyber-physical threats, especially false data injection attacks. We propose a consensus-based estimation algorithm that integrates a nearly-constant-velocity model with saturation-based filtering to suppress impulsive measurement variations and promote robust, distributed state estimation. To counteract adversarial conditions, we incorporate a dynamic false data injection detection and isolation mechanism that uses innovation thresholds to identify and disregard suspicious measurements before they can degrade the global estimate. The effectiveness of the proposed algorithms is demonstrated through a series of simulation-based case studies under both benign and adversarial conditions. The results show that increased network connectivity and higher consensus iteration rates improve estimation accuracy and convergence speed, while properly tuned saturation filters achieve a practical balance between fault suppression and accurate estimation. Furthermore, under localized, coordinated, and transient false data injection attacks, the detection mechanism successfully identifies compromised agents and prevents their data from corrupting the distributed global estimate. Overall, this study illustrates that the proposed algorithm provides a simplified fault-tolerant solution that significantly enhances the accuracy and resilience of distributed target tracking without imposing excessive communication or computational burdens.

Amir Ahmad Ghods, Mohammadreza Doostmohammadian

Faculty of Mechanical Engineering, Semnan University, Iran

False Data Injection Attacks Fault Detection Multi-Agent Consensus

Jul 31, 2026cs.GT

Beyond Byzantine: An Organizational Consensus Algorithm for Self-Interested Agents Under Information Asymmetry

Traditional distributed consensus protocols classify nodes as either honest-but-faulty or actively malicious (Byzantine). However, in organizational structures, departmental agents rarely fit this binary. Instead, they exhibit bounded rationality and self-interested preferences while operating under asymmetric information. This paper presents the Organizational Consensus Algorithm (OCA), a mechanism design framework tailored for internal negotiation and decision coordination. OCA models inter-departmental conflict as an incomplete information dynamic game, integrating internal token staking, an exception-triggered challenge mechanism, and confidence-weighted consensus rules. Rather than enforcing instantaneous total ordering, OCA leverages a retrospective penalty system driven by delayed verifiable outcomes to deter structural bias and reduce exhaustive coordination overhead. A Python simulation prototype was developed to evaluate OCA. Across independent trials with varying organizational scales, OCA reports lower coordination overhead, higher informative reporting rates, and bounded welfare loss in noisy environments. Crucially, these results remain conditional on the stated simulation model and do not by themselves establish a general truthful equilibrium.

Jiawei Zhang, Jianbo Liu

Department of Agricultural Economics Purdue University West Lafayette, USA · Basic Technology Group, Intelligent Terminal Business Dept. JD Logistics, JD.com Beijing, China

Multi-Agent Coordination Mechanism Design Multi-Agent Consensus

Jul 29, 2026cs.CL

Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models

Large language models (LLMs) are increasingly deployed in multi-agent environments. However, the processes by which beliefs form and propagate among interacting LLMs remain poorly understood. We introduce CoevolveSim, a framework for studying belief diffusion within networked LLM populations. CoevolveSim allows us to isolate and study three factors: domain specialization, social-role assignment, and social network structure. Within this framework, generalist and specialist LLM agents exchange and revise beliefs. In each round, an LLM agent observes a summary of its neighbors' beliefs before updating its own. We run 1,280 controlled simulations spanning four scenarios, two network structures, and 20 medical-indication statements. We find that persona-style role assignment and network structure reshape individual belief revision but have minimal effect on population-level consensus. In contrast, introducing (finetuned) specialist LLMs more than doubles the shift in consensus and gives rise to consistent asymmetries in exerted influence. We further show that simple persistence-based opinion-dynamics models reproduce collective outcomes in all-generalist LLM populations, whereas heterogeneous LLM populations require population-level belief composition to reproduce consensus and agent identity to predict individual belief transitions. Our results indicate that realistic simulation of belief diffusion in multi-agent LLM systems requires a diverse set of underlying LLMs, not persona prompting alone.

Germans Savcisens, Samantha Dies, Courtney Maynard +1

Khoury College of Computer Sciences, Northeastern University, Boston, USA · Network Science Institute, Northeastern University, Boston, USA · Santa Fe Institute, Santa Fe, USA

Multi-Agent LLM Systems Agent-Based Modeling Multi-Agent Consensus Large Language Model-Based Social Simulation Multi-Agent Communication

Jul 28, 2026cs.SE

Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges

Multi-Agent Debate (MAD) is a promising paradigm for improving the accuracy and robustness of Large Language Model (LLM)-based agentic systems. It enables multiple agents to exchange arguments, critique each other's outputs, and iteratively converge towards a solution. However, research remains fragmented, with inconsistent terminology and no rigorous synthesis of MAD design dimensions. We present a systematic literature review characterizing 141 primary studies on MAD. We derive a three-dimensional taxonomy covering debate participants, the interaction mechanisms structuring the exchange, and the agreement protocols governing debate resolution, supported by formal notations to render MAD configurations. Our analysis reveals that the field has implicitly converged on a narrow design pattern - static, fully connected topologies, verbatim exchange, short-term memory and voting resolution strategies - adopted by convention rather than systematic comparison, while promising alternatives remain marginal. Because any MAD setting reflects roughly a dozen interacting design decisions, cross-study comparison is unreliable when these are left implicit. We position the taxonomy as a descriptive map of the research landscape, a framework for controlled benchmarking, and potentially as a schema for machine-readable MAD specifications. As future work, we propose formalizing it into an executable specification, enabling cost-aware benchmarking and automated tuning of debate configurations.

Quim Motger, Marc Oriol, Jordi Marco +1

Dpt. of Service and Information System Engineering, Universitat Politècnica de Catalunya, Barcelona, Spain · Dpt. of Computer Science, Universitat Politècnica de Catalunya, Barcelona, Spain

Multi-Agent Debate Multi-Agent Consensus Multi-Agent Communication

Jul 27, 2026cs.MA

Decentralised Consensus Learning Networks: SME Rotation Without Centralised Reward

Centralised reward signals dominate modern AI learning systems, but they impose a single external definition of correct or valuable knowledge. We present a decentralised, consensus-based multi-agent learning framework in which expertise emerges through peer validation rather than prescribed reward. Agents update beliefs via weighted social consensus, while trust is allocated according to competence inferred from peer consistency instead of ground truth. Subject-matter expert (SME) status is assigned dynamically as a top-percentile competence rank rather than a fixed label. We evaluate the framework across 84 simulation runs spanning 30 to 10,000 agents, multiple graph topologies, sparse large-scale networks, scalar and vector belief representations, dimensionality sweeps (D=1-500), multi-seed robustness tests, and parameter sensitivity analyses. Phase 1 shows that SME rotation is robust, persistent, topology-invariant, and scale-invariant: 90-100% of agents attain SME status, with most expertise turnover occurring after belief convergence and increasing with network size. Phases 2 and 3 show that vector beliefs introduce heterogeneous convergence with cascade dynamics and reveal five distinct dynamical regimes as belief dimensionality increases. At high dimensionality (D=150-200), the network reaches stable partial consensus while expertise becomes increasingly concentrated in a single agent. ETA sensitivity analysis demonstrates that this concentration is driven by belief dimensionality rather than stochastic noise. We interpret this behaviour as an emergent property of decentralised learning: in complex high-dimensional consensus spaces, the agent most consistently aligned with the collective belief naturally emerges as the recognised expert.

Florin Neagu

Decentralized Learning Multi-Agent Consensus Emergent Behavior in Multi-Agent Systems

Jul 21, 2026eess.SY

How network perturbations distort agreement trajectories in LTI multi-agent systems

Distributed coordination of multi-agent systems frequently relies on cooperative protocols designed to achieve agreement on a prescribed, non-trivial trajectory. While the robustness of such protocols to various uncertainties is well documented, existing literature universally assumes that the target agreement trajectory itself remains invariant. This assumption may hold in ideal cases, but we prove that network perturbations can vastly modify the asymptotic agreement trajectory. We first investigate the exact trajectories of Linear Time-Invariant (LTI) agents subjected to dynamic coupling uncertainties by establishing a new Laplace-domain criterion that characterizes the specific closed-loop poles governing the perturbed agreement manifold. To formalize our analysis, we introduce the notion of structure-preserving dynamics, perturbations that maintain the null space of the communication graph's Laplacian, and contrast them with transmission only dynamics, affecting only the adjacency matrix. We prove a critical fragility within standard cooperative output regulation schemes: while static consensus is uniquely robust to heterogeneous transmission delays, synchronization to periodic trajectories is destroyed by arbitrarily small transmission delays. Furthermore, we demonstrate that for d-regular topologies, uniform transmission perturbations can easily shift the system to synchronize with an unexpected, entirely new frequency. These findings expose a previously unidentified vulnerability in classical robust synchronization, demonstrating that transmission dynamics necessitate fundamental structural modifications to networked reference generators.

Gal Barkai, Irinel-Constantin Morărescu

Université de Lorraine, CNRS, CRAN, F-54000 Nancy, France

Multi-Agent Coordination Multi-Agent Control Robust Control Multi-Agent Consensus

Jul 16, 2026cs.NI

ANet Patu-1: The Value of Connection in the Agent Network

The Internet taught us that the value of a network depends on \emph{how} its nodes connect: broadcast stars scale as

V\!\propto\!N

(Sarnoff), fully-connected meshes as

N^2

(Metcalfe), and group-forming networks as

2^{N}

(Reed). We ask the analogous question for networks of AI agents. We model the net value of connection as a function of coordination-group size, derive from it the properties an optimal collaboration protocol must have, and introduce ANet Patu-1 -- a self-organizing consensus protocol in which the network continuously re-forms its own coalitions, adaptively riding the upper envelope of all three regimes at

O(1)

parallel consensus rounds. To measure value without opinion-grading, we score an emergent protocol by formally specifying it and deriving its complexity, the way distributed algorithms are analyzed. Two results follow. (i)~Emergence -- a crowd of the \emph{cheapest} model, when heterogeneous, starts weak but its collective value compounds with

N

and \emph{overtakes} a crowd of a far \emph{stronger} model that is homogeneous: a crossover that marks a scaling law for collaboration rather than for scale. (ii)~Reflexivity -- a heterogeneous network, given only its own problem and no design hints, converges on ANet Patu-1 itself, reconstructing the high-dimensional law that governs its own connective value.

Mu Yuan, Jinke Song, Zhaomeng Zhou +1

Agent Network Research · The Chinese University of Hong Kong · Mu Yuan1,2 +5

Multi-Agent Coordination Agent Communication Protocols Multi-Agent Collaboration Multi-Agent Consensus Emergent Behavior in Multi-Agent Systems

Jul 13, 2026cs.AI

Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations

Multi-agent language-model systems increasingly route local interactions, yet the runtime interaction graph is often treated as an implementation detail. We study convention formation in open-weight LM populations spanning 1.1B-32B parameters with a naming-game protocol. Restricted first-token scores over tokenizer-safe labels let us measure prompt-conditioned score-state distributions, construct state-similarity graphs, and separate sampled-label agreement from latent state-space consensus. Across controlled interventions, in the main open-weight repair grids, retained partner-label evidence is necessary but not sufficient: homophilous threshold-similarity routing deletes cross-basin exposure and amplifies fragmentation, while bridge-seeking routing often repairs fragmentation when memory is available. In a three-seed mixed four-model grid, threshold-similarity produces no final behavioral or state consensus in 189 setting-seed runs, whereas state-component and label-disagreement bridges recover final behavioral consensus in 14/18 retained-memory runs. Across homogeneous model populations, retained history generally shifts fragmented dynamics toward consensus; the clearest case is Qwen2.5-32B, which reaches stable behavioral and final state consensus in all 18 retained-history well-mixed settings, while threshold-similarity reaches neither form of consensus in 189 settings. Robustness over state thresholds, population size, and vocabulary size preserves the qualitative ordering, and early-window graph-energy features provide useful within-grid diagnostics.

Samer Saab, Chaouki Abdallah

Lebanese American University Byblos, Lebanon · Electrical and Computer Engineering Department Lebanese American University Byblos, Lebanon

Open-Weight Language Models Multi-Agent Systems Multi-Agent Consensus Multi-Agent LLMs

Jul 11, 2026cs.LG

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution. We study a third signal, free at inference time: cross-model consensus, the degree to which independently trained models, each solving the problem once, agree on a final answer. We treat the panel as an LLM-jury, in which the structure of agreement, not any model's score of another, is the verification signal. Across seven benchmarks it selects correct answers better than self-consistency and far better than a model scoring its own candidates: on competition math it closes the entire gap to an oracle selector, while self-scoring closes almost none. The mechanism is error decorrelation: independently trained models err differently, so their wrong answers scatter while the correct one accumulates agreement. We make this precise with a parameter-free law, derived in closed form, that predicts consensus accuracy from three measured panel statistics to a mean absolute error of

0.03

and exposes the method's ceiling: a shared-error floor where models share a misconception, near zero on math but non-trivial on science. Against four trained verifiers spanning discriminative, outcome, and generative reward models, the free LLM-jury matches the strongest inside their math training domain and is the top selector outside it. Cross-model consensus is thus a verifier we can characterize in advance: a law that says when to trust it, and a floor that marks where it cannot.

Ning Liu

Independent Researcher

LLM Answer Verification Test-Time Scaling Multi-Agent Consensus Language Model Ensembles LLM Reasoning

Jul 7, 2026cs.AI

How Much Does Correctness Cost? Budgeted Placement of Strong Correctors in a Weak Multi-Agent Swarm

A cheap swarm of unreliable agents can be steered to a correct consensus by a few strong, expensive "oracle" correctors. We ask how much one must spend, and where to place the oracles. We model the swarm as a consensus on a graph in which each oracle pins one node toward the truth at a cost-coupled, concave strength, and measure quality by the coherence H(R)=tr M(R)^{-1}. Our first result is that H stays submodular (each added oracle helps less than the last) even when the oracles differ in strength, so a cost-benefit greedy comes within 1-1/e of the best placement at any budget. Inverting the budget gives the budget-correctness frontier B*(eps), the least spend that guarantees an eps-correct consensus: closed-form on the complete graph, and a minimal oracle count k* when oracles cost the same. Whether a budget then buys a few strong oracles or many medium onese curvature of the cost-quality law: diminishing returns favour spreadsharply increasion. Measured onthe Qwen3 ladder (0.6-32B), the law is concave for math verificatio convex foremergent code tracing, so the verdict is genuinely task-dependent.https://github.com/YehudaItkin/budgeted-oracle-placemen

Igor Itkin

Independent Researcher, Tel Aviv, Israel

Submodular Optimization Multi-Agent System Optimization Multi-Agent Coordination Cost-Aware Inference Multi-Agent Consensus

Jul 6, 2026cs.MA

Collective Intelligence with Foundation Models

As foundation models grow in scale and diversity, coordinating multiple models into cooperative reasoning systems offers a path toward safer, more reliable AI. This chapter presents a multi-agent framework where solver models generate independent drafts, each undergoes structured critique and revision by a critic agent, and an aggregator agent synthesizes a final consensus solution. A scoring module provides semantic, numerical, and procedural evaluation across all agents. Through ablation studies on a benchmark spanning calculus, physics, chemistry, biology, economics, optimization, statistics, and mathematics, we isolate the contributions of framework architecture versus model diversity. We compare four configurations: (1) Individual Baseline, (2) Homogeneous Framework using one shared model, (3) Redundant Homogeneous Solvers using multiple instances of the same model, and (4) Heterogeneous Framework with diverse specialized models. Results show that while framework structure and redundant sampling yield modest gains, model heterogeneity is the critical factor driving substantial performance improvements. The heterogeneous configuration achieves superior step-wise accuracy (0.64 vs. 0.54 for individual models; 2.3x improvement over homogeneous configurations) with reduced variance across categories and difficulty levels. Step-wise reasoning quality (correctness of intermediate steps, not just final answers) improves dramatically only with model diversity, showing that heterogeneous agents provide complementary error detection and reasoning refinement essential for explainability and auditability. We discuss architectural principles, evaluation methodology, and implications for Global Applied AI, showing how heterogeneous multi-agent coordination supports transparent, auditable, high-confidence decision-making across scientific and industrial domains.

J. de Curtò, I. de Zarzà

Department of Computer Applications in Science & Engineering, BARCELONA Supercomputing Center, 08034 Barcelona, Spain · Escuela Técnica Superior de Ingeniería (ICAI), Universidad Pontificia Comillas, 28015 Madrid, Spain · Human Centered AI, Data & Software, LUXEMBOURG Institute of Science and Technology, L-4362 Esch-sur-Alzette, Luxembourg

AI Agent Evaluation Multi-Agent Collaboration Multi-Agent Systems Multi-Agent Consensus Language Model Ensembles Multi-Agent Reasoning

Jul 4, 2026cs.LG

Social Networks of LLM Agents

Large language model (LLM) agents are increasingly deployed in interacting populations, raising the question of what such populations come to believe collectively. Whether a population aggregates genuine knowledge or collapses into a false consensus directly affects how much such systems can be trusted. Classical social-network models assume that the network itself determines how beliefs combine. This assumption breaks down for LLM agents, whose limited attention takes in only part of what they are exposed to, so these models overstate how much information a population actually pools and cannot tell genuine consensus from herding. We introduce SNLA, a framework that models how much each agent actually influences others, rather than merely how the network connects them. This influence depends on each agent's position in the network and on how sharply attention focuses. Theoretically, we show on a tractable proxy that narrow attention causes herding, where the effective sample size stays bounded regardless of population size, while wide attention recovers wisdom-of-crowds behavior only when the exposure graph is undirected and degree-regular. Empirically, a controlled testbed validates these predictions directly, and the herding-wisdom transition reproduces on operator-controlled variants of three multi-agent LLM benchmarks.

Kaixuan Liu, Guojun Xiong, Weinan Zhang +1

Department of Computer Science Emory University Atlanta, GA 30322 · School of Computer Science Shanghai Jiao Tong University Shanghai, China

Opinion Dynamics Computational Social Science Multi-Agent Consensus Multi-Agent LLMs Emergent Behavior in Multi-Agent Systems

Jun 28, 2026cs.MA

Minority Sentinel: When to Overturn Majority Voting in Multi-Agent LLM Debates

Multi-Agent Debate (MAD) with Majority Voting is a dominant paradigm for improving LLM reasoning, yet its effectiveness rests on the Condorcet Jury Theorem's assumption of independent errors. Because contemporary LLMs share similar pretraining corpora, their errors are strongly correlated, causing the majority to systematically suppress correct minority opinions, a phenomenon we term Minority Truth. Through debates among three heterogeneous LLM agents on six benchmarks, we find that roughly one in four divergent cases has the minority holding the correct answer, yielding a 10-percentage-point theoretical recovery margin. We propose Minority Sentinel, a lightweight meta-classifier that extracts a multi-dimensional debate fingerprint from debate logs and trains a LightGBM model to decide when to overturn majority voting. Minority Sentinel achieves a stable Flip Precision of 81.2% with positive Net Gain across all six datasets and all 20 random seed trials, demonstrating that debate logs contain sufficient behavioral signals for a non-LLM classifier to reliably recover suppressed minorities without degrading system accuracy. The LLM-as-Judge baseline yields negative Net Gain despite higher recall, confirming that flip safety, not recovery volume, determines intervention value.

Chuan He, Zebin Chen, Zhengyi Yang +5

University of New South Wales · Euler AI · Macquarie University

Multi-Agent Debate Multi-Agent Consensus LLM Agent Reliability Majority Voting

Jun 25, 2026cs.MA

Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement

Multi-agent large language model (LLM) systems often rely on verifier and critic agents to suppress hallucinations, but verification is delayed. During this delay, false claims can propagate through the agent network. We model this process as delayed consensus on a graph with grounded corrector nodes. Spectral decomposition by the grounded Laplacian yields a closed-form stability threshold for the verification dose: correction that is too strong or too delayed can turn consensus into oscillation. The most unstable regime occurs when the communication and verification delays coincide; for delay two, the threshold is the inverse golden ratio. The same framework gives a supermodular placement objective and a greedy (1-1/e)-approximation rule for assigning a limited corrector budget to influential nodes. Experiments across five open models confirm the predicted dose-delay oscillations. By contrast, grounded factual answering makes truth an absorbing boundary and eliminates the effect, suggesting that the instability is specific to signed-belief tasks while grounded verification remains stabilizing

Igor Itkin

Independent Researcher, Tel Aviv, Israel

AI Agent Reliability Multi-Agent Coordination LLM Hallucination Mitigation LLM Agent Verification Multi-Agent Consensus Multi-Agent LLMs

Jun 24, 2026eess.SY

Robustness and Leadership in Markov-switching Consensus Networks

We investigate how time-varying interactions, modeled via a Markov switching graph (MSG), impact the robustness of noisy multi-agent dynamics in both continuous- and discrete-time settings. Our focus is on the steady-state performance of consensus and leader-follower tracking dynamics subject to stochastic noise. Using the framework of Markov jump linear systems (MJLS), we derive expressions for the steady-state covariance of each agent's deviation from consensus and tracking error, respectively, and use them to quantify individual and group performance as a function of the interaction graphs and the switching dynamics. We extend established notions of robustness, certainty indices, and joint centrality from static graphs to the MSG setting. To gain analytical insight, we specialize our results to systems switching between two topologies and characterize how switching influences performance. Numerical simulations further illustrate how switching topologies affects system robustness in both coordination tasks.

Sarah H. Cen, Vaibhav Srivastava, Naomi Ehrich Leonard

Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA · Department of Mechanical and Aerospace Engineering, Princeton University, Princeton, NJ 08544, USA

Multi-Agent Coordination Regime-Switching Dynamical Systems Robust Control Multi-Agent Systems Multi-Agent Consensus

Jun 20, 2026cs.CL

When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societies

LLM "agent societies" are studied via demonstrations of emergent consensus or polarization -- with no measurable control parameter, no theory of when each regime appears, and no test of whether an outcome is a genuine social dynamic or a model artifact. We introduce the coupling gain gamma, measured per-agent by counterfactually perturbing a neighbour's stated opinion. (i) gamma is stable and model-distinguishing -- across five frontier models it spans 0.15-0.43 (n=20, 95% CIs <= 0.025), paraphrase-invariant; social-neighbour gamma roughly equals numeric-anchor gamma, so gamma is evidence-coupling, not uniquely social. (ii) Classical dynamics with measured (not assumed) coefficients organise the regime: Friedkin-Johnsen for consensus/pluralism, signed-Laplacian/structural-balance for polarization. (iii) Frontier LLMs do not spontaneously backfire (beta <= 0), so default societies do not self-polarize -- polarization is always induced; the beta>0 branch arises only in the FJ surrogate, never in the agents. (iv) A randomized-initial-condition diagnostic -- the (slope, bias) of final vs. initial opinion -- separates genuine averaging from model-prior artifacts (boundary-censoring ruled out by construction via interior-valued facts); applied to a published "emergent consensus" result (Chuang et al. 2023) it reveals a model-specific conflation: averaging on debatable claims, prior-artifact on settled facts. (v) Coupling is context-dependent: pairwise gamma does not predict multi-neighbour outcomes -- it can order them backwards -- whereas a modality-matched group coupling does (sixteen closed+open models, Pearson r=-0.70, permutation p=0.008). The regime laws take this matched coupling, not the single-neighbour gamma: emergent consensus must be read from coupling in the target interaction. We contribute a measurement protocol and a validity instrument, not new theory.

Dongxu Yang

DeepLethe

Opinion Dynamics LLM Agent Evaluation Multi-Agent Consensus Multi-Agent LLMs Emergent Behavior in Multi-Agent Systems

Jun 19, 2026cond-mat.dis-nn

Communication Heterogeneity and Collective Consensus in Neural Cellular Automata

Reaching global agreement from purely local interactions is a defining problem of collective intelligence, and most models of it assume that all agents share a single communication protocol. We ask what happens when they do not. Using a Neural Cellular Automaton in which a population of cells must solve the density classification task, agreeing on a global majority that no individual can observe, we introduce languages'' as sub-populations that read one another's messages through a translation with a tunable linguistic distance''. We find that linguistic distance slows consensus, that it produces mild divergence between groups rather than full fragmentation, and that a collective whose shared rule was trained under diverse protocols is robust to mismatch; a homogeneously trained one is not. The findings hold on both a ring and a two-dimensional grid, and admit a natural reading as Ising relaxation, in which a foreign-language region acts as a boundary defect that leaves the system in a higher-energy, partially ordered state. These patterns are qualitatively consistent with effects reported in human group studies, suggesting that distance between communication protocols is a minimal mechanism sufficient to produce them, without anything language-specific.

Nishit Singh

Birla Institute of Technology and Science, Pilani · Pilani, Rajasthan, India

Neural Cellular Automata Multi-Agent Coordination Multi-Agent Consensus Multi-Agent Communication

Jun 15, 2026eess.SY

Distributed Safe Consensus Under Asymmetric Input and Time-Varying Output Constraints

This paper studies safe distributed consensus for single-integrator multi-agent systems over connected undirected graphs under simultaneous asymmetric actuator constraints and output safety constraints. Each agent is equipped with a continuously differentiable asymmetric actuator dynamics that maps a commanded control signal to the realized plant input while keeping the latter strictly inside a prescribed admissible interval. To address output safety, a barrier-coordinate transformation is introduced over a common time-varying safe interval, and a distributed synchronization law is designed in the transformed coordinates. The resulting controller integrates a graph-based coordination layer with an actuator-side tracking layer, thereby enabling simultaneous enforcement of input admissibility, forward invariance of the safe output set, and asymptotic synchronization. For compact admissible sets of initial conditions, it is shown that the closed-loop solution is complete, all signals remain bounded, the actuator inputs remain strictly within their asymmetric bounds, and the agent outputs remain inside the prescribed safe interval for all time. Moreover, the transformed synchronization errors converge exponentially to zero, and the original agent outputs asymptotically synchronize to a designer-selected admissible trajectory embedded in the common safe interval. Numerical simulations validate the proposed framework and demonstrate safe consensus under both asymmetric actuation bounds and time-varying output constraints.

Abhinav Sinha, Shashi Ranjan Kumar

Guidance, Autonomy, Learning, and Control for Intelligent Systems (GALACxIS) Lab, Department of Aerospace Engineering and Engineering Mechanics, University of Cincinnati, OH 45221, USA · Intelligent Systems and Control (ISaC) Lab, Department of Aerospace Engineering, Indian Institute of Technology Bombay, Powai, Mumbai 400076, India

Multi-Agent Coordination Multi-Agent Consensus

Jun 12, 2026cs.MA

Resilient Consensus in Agentic AI

Large language model (LLM) agents are increasingly deployed in multi-agent systems where they must coordinate and agree on shared decisions. We ask whether classical resilient consensus theory, developed for deterministic agents, transfers to LLM agents that may behave adversarially. Framing LLM agreement as a Byzantine consensus game, we run controlled experiments on complete and general communication graphs. We find that prompted LLM agents fail to reach agreement that is achievable in principle: consensus can fail even in settings where classical theory guarantees that a convergent algorithm exists, and this failure persists across temperatures and horizons. At the same time, wrapping the agents with classical resilient consensus filters improves agreement. The benefit of filtering depends on how much robustness the underlying topology already provides. Our results suggest that classical resilient consensus theory is a useful lens for the safety of agentic AI.

Sribalaji C. Anand, George J. Pappas

1KTH, Sweden. · University of Pennsylvania, United States.

Multi-Agent LLM Systems Multi-Agent Consensus LLM Agent Safety LLM Agent Reliability

Jun 11, 2026cs.AI

ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning

Multi-agent debate (MAD) can improve large language model reasoning, but fixed debate pipelines often waste computation and can amplify correlated errors among similar agents. We propose ARMOR-MAD, a training-free heterogeneous MAD framework that treats debate as conditional computation. ARMOR-MAD combines three components: Pre-debate Agreement Routing (PAR) decides whether independently generated Round-0 answers require debate; Early Agreement Stopping Evaluator (EASE) stops debate after convergence; and Semantic Outlier Detection (SOD) down-weights abnormal final answers during aggregation. Across MATH Level 5, GSM8K, MMLU, and MMLU-Pro, ARMOR-MAD consistently improves over fixed-round heterogeneous debate with the same model pool, reaching 65.5%, 96.5%, 90.0%, and 81.5% accuracy, respectively. The results suggest that genuine model heterogeneity and agreement-based control are both important for making MAD more accurate and efficient.

Fuqiang Niu, Bowen Zhang

School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China · School of Artificial Intelligence, Shenzhen Technology University, Shenzhen, China

Multi-Agent Debate Multi-Agent Consensus LLM Routing Multi-Agent Reasoning

Jun 10, 2026cs.MA

CCKS: Consensus-based Communication and Knowledge Sharing

In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable cooperation among agents. However, current action advising approaches often adhere too much to the teacher's guidance without evaluating teacher-student compatibility, which causes excessive advising, suboptimal stability, and degraded performance. To overcome these challenges, this paper presents a Consensus-based Communication and Knowledge Sharing (CCKS) framework, which allows agents to adopt recommendations based on consensus-derived constraints and to follow the teacher's instructions more smartly. This mechanism enables agents to balance exploration and learning from experienced teachers, improving overall performance. The key is the consensus model construction, for which we propose to employ contrastive learning to construct consensus models based on local observations in the agents' training phase. In action selection, agents score and choose actions based on consensus and shared knowledge. Designed as a plug-and-play solution, CCKS integrates seamlessly with existing DTDE algorithms. Experiments conducted in the Google Research Football environment and the complex StarCraft II Multi-Agent Challenge demonstrate that the integration with CCKS significantly improves cooperation efficiency, learning speed, and overall performance compared with current DTDE baselines. The code is available at https://github.com/yuanxpy/CCKS.

Jinyuan Zu, Xiaowei Lv, Yongcai Wang +5

School of Information, Renmin University of China, Beijing 100872, China · State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · The Information Science Academy, China Electronics Technology Group Corporation, Beijing 100043, China +1

Multi-Agent Consensus Decentralized MARL Multi-Agent Communication Cooperative MARL

Jun 7, 2026cs.MA

The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment

Multi-agent LLM systems for medical question answering often treat consensus as a reliability signal: if multiple agents agree on an answer, it is presumed trustworthy. However, answer-level consensus does not entail reasoning-level alignment. We introduce CARA (Cross-Agent Reasoning Alignment), a family of automated metrics that measure whether agents who agree on an answer also agree on the reasoning. Applying CARA to a standard debate system on two medical QA benchmarks, MedQA-USMLE and MedThink-Bench, we identify the consistency illusion: a failure mode where debate reduces detectable contradictions between agents while simultaneously decreasing the semantic similarity of their reasoning chains; agents appear to agree more but reason less consistently. To improve this misalignment, we propose the Grounded Debate Protocol (GDP), a prompt-level intervention that requires agents to commit to named medical facts and take explicit stances on other agents' claims. GDP produces large, consistent alignment improvements, with Cohen's d ranging from +1.43 to +1.99, across two datasets and two backbone models, without adding LLM calls or modifying system architecture. Our results motivate cross-agent reasoning alignment as a quantity to audit alongside accuracy in safety-critical domains.

Xiaoyang Wang, Christopher C. Yang

1Drexel University

LLM Agent Evaluation Multi-Agent Debate Medical QA Multi-Agent Consensus

Jun 5, 2026cs.MA

Modelling Opinion Dynamics at Scale with Deep MARL

Modelling opinion dynamics typically relies on hand-crafted local interaction rules to study emergent macroscopic phenomena such as consensus and polarisation. In contrast, multi-agent reinforcement learning (MARL) enables agents to learn such behaviours directly by optimising simple rewards. To explore the potential of MARL for opinion dynamics, we introduce a GPU-accelerated consensus and truth-finding game that scales to populations of up to 1000 agents, comparable to many real-world social sub-networks. To prevent unrealistic conventions, we extend other-play to general-sum social interactions. We next validate our model on a subset of the Bluesky network by recovering agent importance structures from graph topology alone via a learned attention layer, finding that highly conforming populations most closely match human data. In large social media networks such high levels of conformity significantly reduce collective accuracy and promote dishonest agents that lie to fit in. By contrast, small, dynamic hunter-gatherer networks are less affected; here, conformity can even improve collective agreement. This suggests a mismatch between evolved human conformity heuristics and modern social media environments as a potential contributor to misinformation.

Lukas Seier, Brandon Kaplowitz, Sebastian Towers +2

FLAIR University of Oxford United Kingdom · OWL University of Oxford United Kingdom · OUCE University of Oxford United Kingdom

Opinion Dynamics Multi-Agent Consensus Multi-Agent Reinforcement Learning Emergent Behavior in Multi-Agent Systems

Jun 2, 2026cs.MA

Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions

How much should an LLM agent remember, and how should multi-agent systems be connected when trying to reach consensus? We show these two design choices interact in a way that flips the sign of memory's effect on coordination. Across 432 simulation runs of a networked Naming Game on eight fixed 16-agent topologies, we vary memory depth and network structure. Longer memory slows the time to reach steady state in decentralized networks but accelerates it in centralized ones; the same parameter pushes the system in opposite directions depending on topology. Critically, "faster settling" in centralized networks means locking in to a fragmented plateau more quickly, not reaching system-wide consensus, which can be used to generate diverging opinions. We further document a memory-mediated speed-unity trade-off: centralized networks consistently preserve more competing conventions than decentralized networks, but their settling speed depends sharply on memory. At the agent level, within-network analyses show that high-betweenness bridges suffer a brokerage penalty while agents in locally clustered neighborhoods achieve higher coordination success. Finally, in search of analytically tractable generative mechanisms, we find that agents' choices are well captured by Fictitious Play, indicating belief-based rather than reward-based adaptation. The practical implication: memory depth and communication topology should be co-designed, not optimized in isolation.

Aliakbar Mehdizadeh, Martin Hilbert

Department of Communication University of California, Davis

Agent Memory Multi-Agent Coordination Multi-Agent Consensus Emergent Behavior in Multi-Agent Systems

Jun 2, 2026cs.CL

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

Jun 1, 2026cs.RO

Network Distributed Multi-Agent Reinforcement Learning for Consensus Control of Quadcopters

This paper proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework for quadcopter consensus control. Compared to conventional multi-agent MARL formulations that rely on centralized planning or fully decentralized execution, ND-MARL incorporates the swarm communication graph into the decision process. Under a 2-Neighbor communication topology, each agent observes information of only two neighbors and outputs an action through a distributed policy. A high-level distributed consensus planner is trained using Multi-Agent Soft Actor-Critic (MASAC) and embedded in a hierarchical stack to generate reference target positions tracked by a low-level quadcopter controller. Results demonstrate smooth consensus trajectories and planner-tracker integration when compared to a centralized MARL controller. Most notably, the learned controller exhibits zero-shot scalability, as policies trained on a three-agent system are deployed to swarms of up to 250 agents under the same 2-Neighbor communication topology without retraining or fine-tuning, achieving consistent convergence with increasing steady-state spread at large team sizes due to sparse information propagation. These findings highlight ND-MARL as a stable framework for distributed, communication-aware quadcopter consensus control.

Youssef Mahran, Zeyad Gamal, Aamir Ahmad +1

Mechatronics Engineering Department, German University in Cairo (GUC), Egypt · Institute of Flight Mechanics and Control (IFR), Head of Flight Robotics, University of Stuttgart, Germany · Faculty of EMS, Head of Mechatronics Engineering Department, German University in Cairo (GUC), Egypt

Multi-Agent Control Quadrotor Control Multi-Agent Consensus Decentralized MARL Multi-Agent Communication

Jun 1, 2026cs.MA

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+1

Jun 1, 2026cs.CL

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity

Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers. A key risk is conformity: a model may abandon its own answer simply because others agree on a different one. Prior studies show that LLMs often revise toward a majority answer, but it remains unclear whether these revisions help correct mistakes as often as they introduce new errors. In this paper, we conduct a controlled study in which an LLM first answers a question, then sees simulated peer responses before making a final decision. We manipulate two social cues: consensus structure and authority labels assigned to peers, and measure how they influence beneficial and harmful revisions. Across four open-weight LLMs and seven QA datasets, we find that peer agreement makes it much easier to mislead initially correct models than to correct initially wrong ones. Authority labels make models more likely to choose the endorsed answer, regardless of whether it is correct. More concerningly, generic reasoning interventions such as chain-of-thought and reflection do not reliably reduce harmful revision while preserving beneficial revision. These findings suggest that multi-agent LLM systems should verify peer answers rather than simply aggregate them.

Jiaming Qu, Lucheng Fu, Yibo Hu

Amazon · Georgia Institute of Technology · Illinois Institute of Technology

Multi-Agent LLM Systems Normative Conformity in Language Models Knowledge Conflicts in Language Models Multi-Agent Consensus

May 29, 2026cs.LG

Learning Multi-Agent Coordination via Sheaf-ADMM

We present a differentiable optimization framework for multi-agent coordination. An input is decomposed into overlapping local views, each processed by an agent that solves a convex subproblem parameterized by a neural encoder. Agents coordinate through the Alternating Direction Method of Multipliers (ADMM) with inter-agent constraints specified by a cellular sheaf. The sheaf specifies which aspects of neighboring solutions must agree, allowing for heterogeneous notions of global consensus. Backpropagating through the unrolled optimization jointly trains all components of the multi-agent system. We evaluate on maze pathfinding, image classification, and Sudoku, where agents with individually insufficient local views learn to coordinate to produce correct global outputs. On MNIST, the local-view decomposition yields improved robustness to distribution shifts relative to a standard CNN. On Sudoku, the optimization-derived structure yields markedly higher solve rates than parameter-matched MPNN baselines. Finally, the ADMM structure exposes distinct primal, consensus, and dual state variables, opening the coordination dynamics to direct analysis and intervention -- a property unavailable in standard message-passing architectures.

Jeffrey Seely, Bartłomiej Cupiał, Llion Jones

Sakana AI, Tokyo, Japan · University of Warsaw · AKCES NCBR

Multi-Agent System Optimization Multi-Agent Coordination Alternating Direction Method of Multipliers Multi-Agent Consensus Differentiable Optimization

May 29, 2026cs.CV

Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence

Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spots, aggregating diverse perspectives via multi-agent collaboration has emerged as a promising paradigm. While this approach has shown great success in textual QA, its potential in the multimodal domain remains under-explored. Existing multi-agent VQA methods predominantly adapt text-centric protocols, focusing on textual discussions while ignoring the alignment of visual information. In this work, we reveal a key insight: answer-level agreement is insufficient for reliable multi-agent VQA; \textit{aligned visual evidence} -- shared support from the image regions agents rely on -- is essential for trustworthy consensus. To leverage this insight, we propose EAGLE (\textbf{E}vidence-\textbf{A}ligned \textbf{G}rounded mu\textbf{L}ti-agent r\textbf{E}asoning), a training-free evidence-centered framework for coordinating multiple VLM agents. EAGLE explicitly exposes each agent's grounding regions as visual evidence, enables mutual verification over the evidence, and uses evidence consistency to guide final decision-making. Experiments on six VQA benchmarks show that EAGLE achieves best average performance across domains while remaining lightweight, interpretable, and practical for deployment.

Yuhan Wang, Shuochen Chang, Yalin Feng +8

Peking University · Shanghai Jiao Tong University · Nanyang Technological University +2

Multi-Agent Collaboration VLM Reasoning Multi-Agent Consensus Vision-Language Alignment Multimodal Understanding

May 28, 2026cs.CL

Counterfactual Graph for Multi-Agent LLM Calibration

Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same answer, that answer is assumed to be more reliable. We show that this assumption can fail after agents communicate. Communication can induce correlated failures and false consensus, so the same vote share may reflect reliable agreement in one topology but over-confidence in another. We propose CAGE-CAL, a counterfactual agent-graph calibration framework for multi-agent LLMs. For each query, CAGE-CAL compares an observed post-communication agent graph with a matched counterfactual no-communication graph, capturing both pairwise failure correlations and group-level dependencies. Rather than simply counting how many agents agree, CAGE-CAL estimates the counterfactual shift between observed and no-communication dependence, and calibrates confidence accordingly. Across five benchmarks, CAGE-CAL improves reliability discrimination with competitive ECE, and its calibrated confidence further improves topology selection over the best fixed-topology strategy.

Jiatan Huang, Mingchen Li, Ziming Li +3

University of Connecticut · University of Massachusetts, Amherst

AI Agent Reliability Language Model Calibration Multi-Agent Consensus Causal Interventions in Language Models Multi-Agent Communication LLM Agent Reliability

May 28, 2026cs.MA

CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent Systems

Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over single agent systems, they lead to huge computational overheads because of heavy communication between agents. Previous research has made efforts to train a sparse multi-agent graph or fine-tune a planner to orchestrate the workflow better. However, such extra training processes introduce computational costs and limit MAS to specific domains, therefore compromising their generalizability. In this paper, we propose CONCAT, a training-free multi-agent collaboration framework based on CONsensus and Confidence-driven Ad hoc Teaming to efficiently organize agent interactions. Specifically, agents are clustered based on their initial answers, and leaders of each cluster are selected based on the agents' confidence. Then, a heuristic function based on the Theory of Mind is designed to predict the collaboration benefits between every two leaders according to their answers and confidence. Finally, an ad hoc multi-agent network is organized after evicting a percentage of communications based on the predicted benefits. Experiments across three LLMs and three benchmarks show that CONCAT achieves up to 2.02x higher efficiency (accuracy/latency ratio) than LLM-Debate and outperforms training-aware methods such as AgentDropout, while reducing average latency by 50.1% on Qwen2.5-14B-Instruct, without any task-specific training.

Ziyang Ma, Dingyi Zhang, Sichu Liang +4

Southeast University · Huawei Technologies Ltd

Multi-Agent System Optimization Multi-Agent Orchestration Multi-Agent Collaboration Multi-Agent Consensus Ad Hoc Teamwork Multi-Agent Communication

May 18, 2026cs.LG

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