Multi-Agent Consensus

Ask about this topic

Overview

Multi-agent consensus studies how autonomous systems influence one another to agree on beliefs, decisions, estimates, or coordinated actions. Methods range from graph-based consensus protocols and distributed control to voting, debate, confidence weighting, evidence checking, and adaptive communication. Applications include robot teams, distributed sensing, and groups of language models that deliberate or verify answers. A central tension is that agreement can speed coordination but does not guarantee correctness: shared errors, conformity, adversarial agents, and network structure can all make consensus unreliable.

Latest papers

CardsList

126 papers20 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

May 1, 2026

Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization

Distributed blackbox consensus optimization is a fundamental problem in multi-agent systems, where agents must improve a global objective using only local objective queries and limited neighbor communication. Existing methods largely rely on handcrafted update rules and static cooperation patterns, which often struggle to balance local adaptation, global coordination, and communication efficiency in heterogeneous nonconvex environments. In this paper, we take an initial step toward trajectory-driven self-design for distributed black-box consensus optimization. We first redesign the agent-level swarm dynamics with an adaptive internal mechanism tailored to decentralized consensus settings, improving the balance between exploration, convergence, and local escape. Built on top of this adaptive execution layer, we propose Learning to Act and Cooperate (LACMAS), a trajectorydriven framework in which large language models provide sparse highlevel guidance for shaping both agentinternal action behaviors and agentexternal cooperation patterns from historical optimization trajectories. We further introduce a phased cognitive scheduling strategy to activate different forms of adaptation in a resource-aware manner. Experiments on standard distributed black-box benchmarks and real-world distributed tasks show that LAC-MAS consistently improves solution quality, convergence efficiency, and communication efficiency over strong baselines, suggesting a practical route from handcrafted distributed coordination toward self-designing multi-agent optimization systems.

Zi-Bo Qin, Feng-Feng Wei, Tai-You Chen +1

School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.

Multi-Agent System OptimizationMulti-Agent CoordinationBlack-Box OptimizationDistributed OptimizationLarge Language Model-Guided OptimizationMulti-Agent Consensus
AskPDF
Apr 30, 2026

The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms

As AI transitions toward multi-agent systems (MAS) to solve complex workflows, research paradigms operate on the axiomatic assumption that agent collaboration mirrors the "Wisdom of the Crowd". We challenge this assumption by formalizing the Consensus Paradox: a phenomenon where agentic swarms prioritize internal architectural agreement over external logical truth. Through a 36 experiments encompassing 12,804 trajectories across three state-of-the-art (SOTA) benchmarks (GAIA, Multi-Challenge, and SWE-bench), we prove the Inverse-Wisdom Law: in kinship-dominant swarms, adding logical agents increases the stability of erroneous trajectories rather than the probability of truth. The introduction of additional logical audits converges the system toward a Logic Saturation where internal entropy hits zero while factual error hits unity. By evaluating the interaction between the 3 preeminent SOTA models (Gemini 3.1 Pro, Claude Sonnet 4.6, and GPT-5.4), we establish the Architectural Tribalism Asymmetry as a mechanistic law of transformer weights. We demonstrate that terminal swarm integrity is strictly gated by the synthesizer's receptive logic, rather than aggregate agent quality. We define the Tribalism Coefficient and the Sycophantic Weight as the primary mechanistic determinants of swarm failure. Finally, we establish the Heterogeneity Mandate as a foundational safety requirement for resilient agentic architectures.

Dahlia Shehata, Ming Li

University of Waterloo · Canada

Multi-Agent LLM SystemsMulti-Agent CoordinationMulti-Agent SystemsMulti-Agent ConsensusMulti-Agent ReasoningLLM Agent Reliability
AskPDF
Apr 29, 2026

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

Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review filters hallucinations. Yet the failure dynamics of homogeneous debate remain poorly understood, therefore we report findings from a controlled empirical study of teams of N=10N{=}10 homogeneous agents (Qwen2.5-7B, Llama-3.1-8B, Ministral-3-8B) across R=3R{=}3 debate rounds on two high-difficulty benchmarks (GSM-Hard and MMLU-Hard). We compare peer debate against isolated self-correction and a stochastic noise control that injects rationales from unrelated problems. We decompose debate failure into three model-dependent pathways: sycophantic conformity, where agents uncritically adopt majority answers (modal adoption up to 85.5%); contextual fragility, where peer rationales destabilize previously correct reasoning (vulnerability rate up to 70.0%); and consensus collapse, where plurality voting discards correct answers already present in the generation pool (oracle gap up to 32.3 percentage points). Ablations over communication density (K∈{2,4,9}K \in \{2,4,9\}) and sampling temperature (T∈{0.4,0.7}T \in \{0.4, 0.7\}) show that conformity reaches high levels at minimal peer exposure (K=2K{=}2) and intensifies with greater initial diversity. Across all configurations, debate consumes 2.1-3.4×\times more tokens (up to 28,631 tokens per problem) than self-correction for equal or lower accuracy. Our results indicate that, within the 7-8B parameter class, homogeneous teams without structured roles do not benefit from unguided peer exchange, and that isolated self-correction consistently offers a more favorable cost-accuracy tradeoff.

Blaž Bertalanič, Carolina Fortuna

Jožef Stefan Institute Ljubljana, Slovenia

LLM Self-CorrectionAI Agent EvaluationMulti-Agent DebateMulti-Agent Consensus
AskPDF
Apr 29, 2026

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

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

Ariel Sela

Tel Aviv University

Multi-Agent LLM SystemsMulti-Agent CoordinationMulti-Agent SystemsMulti-Agent ConsensusMulti-Agent ReasoningMulti-Agent Deliberation
AskPDF
Apr 21, 2026

TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems

In open-ended domains, teams must reconcile diverse viewpoints to produce strong deliverables. Answer aggregation approaches commonly used in closed domains are ill-suited to this setting, as they tend to suppress minority perspectives rather than resolve underlying disagreements. We present TeamFusion, a multi-agent system designed to support teamwork in open-ended domains by: 1. Instantiating a proxy agent for each team member conditioned on their expressed preferences; 2. Conducting a structured discussion to surface agreements and disagreements; and 3. Synthesizing more consensus-oriented deliverables that feed into new iterations of discussion and refinement. We evaluate TeamFusion on two teamwork tasks where team members can assess how well their individual views are represented in team decisions and how consensually strong the final deliverables are, finding that it outperforms direct aggregation baselines across metrics, tasks, and team configurations.

Jiale Liu, Victor S. Bursztyn, Lin Ai +4

Pennsylvania State University · Adobe Research · Columbia University +1

Multi-Agent CoordinationMulti-Agent CollaborationMulti-Agent ConsensusHuman-AI Collaboration
AskPDF
Apr 18, 2026

The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration

Multi-agent large language model (LLM) architectures increasingly rely on response-level aggregation, such as Majority Voting (MAJ), to raise reasoning ceilings. However, in open environments, agents are highly susceptible to stealthy contextual corruption, such as targeted prompt injections. We reveal a critical structural vulnerability in current multi-agent systems: response-level aggregation collapses when corrupted agents form a local majority. Because voting aggregates fully-formed conclusions, it is blind to flawed intermediate logic. To overcome this systematic limitation, we propose the Token-Level Round-Robin (RR) Collaboration, where agents sequentially interleave generation within a shared auto-regressive context. We formalize this process as a discrete-time dynamical system, proving that token-level interleaving transitions aggregation from a brittle counting of final votes (a linear sum) to a dynamic, interwoven chain of logic (a non-linear operator product). Through this theoretical lens, we prove that the honest model's restorative pull can overpower adversarial corruptions, even when corrupted agents form a majority. We conduct an exhaustive empirical evaluation across diverse reasoning benchmarks and demonstrate that while MAJ collapses when corrupted agents reach a majority, RR maintains robust accuracy well beyond this critical threshold.

Jiayuan Liu, Shiyi Du, Weihua Du +2

Carnegie Mellon University · Foundations of Cooperative AI Lab (FOCAL) · Adelaide University

Multi-Agent LLM SystemsAdversarial RobustnessMulti-Agent ConsensusMulti-Agent Reasoning
AskPDF
Apr 15, 2026

Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus

Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple interacting agents. However, such decomposition often introduces additional challenges, including non-stationarity, unstable training, weak coordination, and limited theoretical guarantees. In this paper, we propose the Consensus Multi-Agent Transformer (CMAT), a centralized framework that bridges cooperative MARL to a hierarchical single-agent reinforcement learning (SARL) formulation. CMAT treats all agents as a unified entity and employs a Transformer encoder to process the large joint observation space. To handle the extensive joint action space, we introduce a hierarchical decision-making mechanism in which a Transformer decoder autoregressively generates a high-level consensus vector, simulating the process by which agents reach agreement on their strategies in latent space. Conditioned on this consensus, all agents generate their actions simultaneously, enabling order-independent joint decision making and avoiding the sensitivity to action-generation order in conventional Multi-Agent Transformers (MAT). This factorization allows the joint policy to be optimized using single-agent PPO while preserving expressive coordination through the latent consensus. To evaluate the proposed method, we conduct experiments on benchmark tasks from StarCraft II, Multi-Agent MuJoCo, and Google Research Football. The results show that CMAT achieves superior performance over recent centralized solutions, sequential MARL methods, and conventional MARL baselines. The code for this paper is available at:https://github.com/RS2002/CMAT .

Zijian Zhao, Jing Gao, Sen Li

1The Hong Kong University of Science and Technology · 2The Hong Kong Polytechnic University · 3The Hong Kong University of Science and Technology (Guangzhou)

Cooperative MARLMulti-Agent Reinforcement LearningMulti-Agent CoordinationTransformer-Based RLMulti-Agent Consensus
AskPDF
Apr 9, 2026

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

Multi-agent debate improves LLM reasoning, yet agreement is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus stopping commits that error to automated action with no recourse. We introduce Conformal Social Choice, a post-hoc layer that converts debate outputs into calibrated act-versus-escalate decisions. Verbalized probability distributions from heterogeneous agents are aggregated via a linear opinion pool and calibrated with split conformal prediction, yielding fixed-round marginal coverage: at any pre-specified round, the correct answer is included with probability ≥ 1−α{\geq}\,1{-}α, without assumptions on individual model calibration. A hierarchical action policy maps singletons to autonomous action and larger sets to human escalation. Across eight MMLU-Pro domains and two additional benchmarks, fixed-round coverage stays close to target. The key finding is not that debate becomes more accurate, but that the conformal layer makes its failures actionable: at the final round, 81.9% of wrong-consensus cases are flagged by non-singleton sets at α=0.05α{=}0.05. Separately, among cases that reach a singleton before the final round, accuracy reaches 90.0--96.8% on MMLU-Pro (up to 22.1pp above consensus stopping): a selection effect, not a reasoning improvement. Simple probability- and entropy-threshold rules attain comparable interception; conformal's distinct value is a finite-sample fixed-round coverage guarantee together with explicit candidate sets for escalation. Adaptive first-singleton stopping is evaluated empirically and not covered by this guarantee.

Mengdie Flora Wang, Haochen Xie, Guanghui Wang +9

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

LLM Agent SafetySelective PredictionMulti-Agent DeliberationConformal PredictionMulti-Agent DebateMulti-Agent Consensus
AskPDF
Apr 8, 2026

Event-Triggered Adaptive Consensus for Multi-Robot Task Allocation

Coordinating robotic swarms in dynamic and communication-constrained environments remains a fundamental challenge for collective intelligence. This paper presents a novel framework for event-triggered organization, designed to achieve highly efficient and adaptive task allocation in a heterogeneous robotic swarm. Our approach is based on an adaptive consensus mechanism where communication for task negotiation is initiated only in response to significant events, eliminating unnecessary interactions. Furthermore, the swarm self-regulates its coordination pace based on the level of environmental conflict, and individual agent resilience is managed through a robust execution model based on Behavior Trees. This integrated architecture results in a collective system that is not only effective but also remarkably efficient and adaptive. We validate our framework through extensive simulations, benchmarking its performance against a range of coordination strategies. These include a non-communicating reactive behavior, a simple information-sharing protocol, the baseline Consensus-Based Bundle Algorithm (CBBA), and a periodic CBBA variant integrated within a Behavior Tree architecture. Furthermore, our approach is compared with Clustering-CBBA (C-CBBA), a state-of-the-art algorithm recognized for communication-efficient task management in heterogeneous clusters. Experimental results demonstrate that the proposed method significantly reduces network overhead when compared to communication-heavy strategies. Moreover, it maintains top-tier mission effectiveness regarding the number of tasks completed, showcasing high efficiency and practicality. The framework also exhibits significant resilience to both action execution and permanent agent failures, highlighting the effectiveness of our event-triggered model for designing adaptive and resource-efficient robotic swarms for complex scenarios.

Fidel Aznar, Mar Pujol, Álvaro Díez

Department of Computer Science and Artificial Intelligence, University of Alicante, Alicante, Spain

Multi-Robot Task AllocationSwarm RoboticsMulti-Agent Consensus
AskPDF
Apr 4, 2026

Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus

Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majority vote, implicitly assuming that agents contribute complementary evidence. We embed each agent's chain-of-thought rationale and measure pairwise similarity: across 100 GSM8K questions with three Qwen2.5-14B agents, mean cosine similarity is 0.888 and effective rank is 2.17 out of 3.0, a failure mode we term representational collapse. DALC, a training-free consensus protocol that computes diversity weights from embedding geometry, reaches 87% on GSM8K versus 84% for self-consistency at 26% lower token cost. Ablation experiments reveal 1-3 point per-protocol run-to-run variance, confirm that hint sharing contributes more than diversity weighting alone, and show that encoder choice strongly modulates collapse severity (cosine 0.908 with mxbai versus 0.888 with nomic) and downstream accuracy. The more robust finding is that collapse is measurable, worsens on harder tasks, and that the choice of embedding proxy is a first-order design decision for any latent communication protocol.

Dipkumar Patel

LLMs Research Inc.

Multi-Agent Consensus
AskPDF
Apr 4, 2026

DejaVu: A Minimalistic Mechanism for Distributed Plurality Consensus

We study the plurality consensus problem in distributed systems where a population of extremely simple agents, each initially holding one of kk opinions, aims to agree on the initially most frequent one. In this setting, hh-majority is arguably the simplest and most studied protocol, in which each agent samples the opinion of hh neighbors uniformly at random and updates its opinion to the most frequent value in the sample. We propose a new, extremely simple mechanism called DéjàVu: an agent queries neighbors until it encounters an opinion for the second time, at which point it updates its own opinion to the duplicate value. This rule does not require agents to maintain counters or estimate frequencies, nor to choose any parameter (such as a sample size hh); it relies solely on the primitive ability to detect repetition. We provide a rigorous analysis of DéjàVu that relies on several technical ideas of independent interest and demonstrates that it is competitive with hh-majority and, in some regimes, substantially more communication-efficient, thus yielding a powerful primitive for plurality consensus.

Francesco d'Amore, Niccolò D'Archivio, George Giakkoupis +2

Gran Sasso Science Institute, Italy · INRIA, COATI, Université Côte d’Azur, France · INRIA Rennes

Multi-Agent Consensus
AskPDF
Apr 3, 2026

HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate

Multi-Agent Debate (MAD) is a collaborative framework in which multiple agents iteratively refine solutions through the generation of reasoning and alternating critique cycles. Current work primarily optimizes intra-round topologies and inter-round interactions separately, limiting the adaptation of token costs to task complexity. This work introduces Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate (HCP-MAD), leveraging consensus as a dynamic signal to facilitate progressive reasoning. The core motivation is that a majority of straightforward tasks can be effectively resolved via lightweight pair-agent debates, while complex tasks require expanded collaboration. Firstly, Heterogeneous Consensus Verification conducts rapid consensus verification using a pair of heterogeneous agents for early stopping. Next, Heterogeneous Pair-Agent Debate applies an adaptive stopping criterion to terminate mutual critique of reasoning traces. Finally, the unresolved tasks are addressed through Escalated Collective Voting by aggregating diverse perspectives from additional agents. Experiments across six benchmarks show that HCP-MAD enhances accuracy while substantially reducing token costs. Code is https://github.com/fuyu66/HCP-MAD.

Yiqing Liu, Hantao Yao, Wu Liu +2

University of Science and Technology of China

Multi-Agent DebateMulti-Agent ReasoningMulti-Agent CollaborationMulti-Agent Consensus
AskPDF
Apr 1, 2026

GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization

Non-stationarity arises from concurrent policy updates and leads to persistent environmental fluctuations. Existing approaches like Centralized Training with Decentralized Execution (CTDE) and sequential update schemes mitigate this issue. However, since the perception of the policies of other agents remains dependent on sampling environmental interaction data, the agent essentially operates in a passive perception state. This inevitably triggers equilibrium oscillations and significantly slows the convergence speed of the system. To address this issue, we propose Gradient Realignment via Active Shared Perception (GRASP), a novel framework that defines generalized Bellman equilibrium as a stable objective for policy evolution. The core mechanism of GRASP involves utilizing the independent gradients of agents to derive a defined consensus gradient, enabling agents to actively perceive policy updates and optimize team collaboration. Theoretically, we leverage the Kakutani Fixed-Point Theorem to prove that the consensus direction u∗u^* guarantees the existence and attainability of this equilibrium. Extensive experiments on StarCraft II Multi-Agent Challenge (SMAC) and Google Research Football (GRF) demonstrate the scalability and promising performance of the framework.

Sihan Zhou, Tiantian He, Yifan Lu +2

College of Computer Science and Technology, and Key Laboratory of Social Computing and Cognitive Intelligence (Ministry of Education), Dalian University of Technology, China · Center for Frontier AI Research, Institute of High Performance Computing, Singapore Institute of Manufacturing Technology, Agency for Science, Technology and Research (A*STAR), Singapore · School of Computer Science and Engineering, Nanyang Technological University, Singapore

Cooperative MARLNon-Stationary RLMulti-Agent ConsensusGradient Descent Dynamics
AskPDF
Mar 31, 2026

One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction

Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies sample from one role-conditioned distribution, and multi-agent frameworks use fixed roles with flat majority voting, discarding the diagnostic signal in disagreement. We propose CAMP (Case-Adaptive Multi-agent Panel), where an attending-physician agent dynamically assembles a specialist panel tailored to each case's diagnostic uncertainty. Each specialist evaluates candidates via three-valued voting (KEEP/REFUSE/NEUTRAL), enabling principled abstention outside one's expertise. A hybrid router directs each diagnosis through strong consensus, fallback to the attending physician's judgment, or evidence-based arbitration that weighs argument quality over vote counts. On diagnostic prediction and brief hospital course generation from MIMIC-IV across four LLM backbones, CAMP consistently outperforms strong baselines while consuming fewer tokens than most competing multi-agent methods, with voting records and arbitration traces offering transparent decision audits.

Yuxing Lu, Yushuhong Lin, Jason Zhang

Georgia Institute of Technology · Peking University

Multi-Agent CollaborationClinical PredictionLLM Agent OrchestrationClinical ReasoningMulti-Agent Consensus
AskPDF
Mar 28, 2026

The impact of multi-agent debate protocols on debate quality: a controlled case study

In multi-agent debate (MAD) systems, performance gains are often reported; however, because the debate protocol (e.g., number of agents, rounds, and aggregation rule) is typically held fixed while model-related factors vary, it is difficult to disentangle protocol effects from model effects. To isolate these effects, we compare three main protocols, Within-Round (WR; agents see only current-round contributions), Cross-Round (CR; full prior-round context), and novel Rank-Adaptive Cross-Round (RA-CR; dynamically reorders agents and silences one per round via an external judge model), against a No-Interaction baseline (NI; independent responses without peer visibility). In a controlled macroeconomic case study (20 diverse events, five random seeds, matched prompts/decoding), RA-CR achieves faster convergence than CR, WR shows higher peer-referencing, and NI maximizes Argument Diversity (unaffected across the main protocols). These results reveal a trade-off between interaction (peer-referencing rate) and convergence (consensus formation), confirming protocol design matters. When consensus is prioritized, RA-CR outperforms the others.

Ramtin Zargari Marandi

Multi-Agent DebateMulti-Agent CommunicationMulti-Agent Consensus
AskPDF
Mar 27, 2026

Deliberative Curation: A Protocol for Multi-Agent Knowledge Bases

As AI agents transition from isolated tools to collaborative participants in shared knowledge ecosystems, governing collective knowledge curation becomes a critical challenge. Human platform governance mechanisms do not transfer directly: agent statelessness undermines deterrence-based sanctions, model homogeneity violates independence assumptions underlying crowd wisdom, and sycophancy collapses deliberative consensus. We propose a deliberative curation protocol combining three governance layers: (1) a knowledge artifact lifecycle formalized as a labeled transition system; (2) reputation-weighted deliberative voting integrating Beta Reputation with EigenTrust amplification; and (3) graduated sanctions adapted for stateless agents, including broken agent handling distinguishing malfunction from adversarial behavior. We evaluate the protocol through agent-based simulation with 100 agents across seven behavioral archetypes under two adversity scenarios (30 seeds, paired t-tests). The protocol trades modest precision under benign conditions for substantially better resilience under adversity: 0.826 vs 0.791 for majority vote under moderate adversity (p<0.001), widening to 0.807 vs 0.740 under stress (p<0.001). The protocol degrades roughly three times more slowly than majority vote. Ablation analysis identifies commit-reveal vote concealment as the most impactful single component (8.2-8.6pp precision improvement, p<0.001), outperforming reputation weighting and deliberation combined. Graduated sanctions were not exercised in simulation and remain empirically unvalidated.

Steven Johnson

AI Agent GovernanceMulti-Agent Consensus
AskPDF
Mar 26, 2026

Emergent Collaborative Deliberation in Multi-Model AI Systems: A BFT-Derived Protocol for Epistemic Synthesis

We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model disagreement as epistemic signal rather than error. The protocol assigns engineered cognitive personas to language models -- separating what a model is from how it reasons -- and introduces an In-Sample/Out-of-Sample validation framework adapted from quantitative finance to distinguish training-data consensus from empirically grounded conclusions. Across 1,478 deliberation sessions spanning 32 topics in 10 domain categories, we demonstrate that (1) the cognitive persona, not the underlying model, determines epistemic behavior: free edge-inference models costing 0.0002 USD per batch produced comparable analytical output to frontier models costing 10.69 USD; (2) RLHF alignment training creates measurable, domain-specific epistemic blind spots -- contested policy topics exhibit 12.3 percentage points less adversarial challenge than settled science topics, and AI safety topics show asymmetric bias (ΔΔ=11.6%) where models challenge claims that AI is dangerous far more vigorously than claims that AI risk is overstated; (3) the protocol exhibits no directional bias of its own (immigration ΔΔ=2.3%, renewables ΔΔ=1.2%); and (4) out-of-sample evidence retrieval validated 239 claims with 100% evidence retrieval and surfaced 167 blind-spot discoveries invisible to training-data deliberation. Run-to-run reproducibility across randomized model×\timespersona assignments averages ±\pm2.2% standard deviation. Total cost for the complete battery including all overhead: 217 USD. We release the protocol specification under MIT license to enable independent verification.

VD Doske

Independent Researcher / Consilia

Multi-Agent DebateMulti-Agent ConsensusLanguage Model Bias Evaluation
AskPDF
Mar 25, 2026

When Is Collective Intelligence a Lottery? Multi-Agent Scaling Laws for Memetic Drift in LLMs

Multi-agent systems powered by large language models (LLMs) are increasingly deployed in settings that shape consequential decisions, both directly and indirectly. Yet it remains unclear whether their outcomes reflect collective reasoning, systematic bias, or mere chance. Recent work has sharpened this question with naming games, showing that even when no individual agent favors any label a priori, populations rapidly break symmetry and reach consensus. Here, we reveal the mechanism by introducing a minimal model, Quantized Simplex Gossip (QSG), and trace the microscopic origin of this agreement to mutual in-context learning. In QSG, agents maintain internal belief states but learn from one another's sampled outputs, so one agent's arbitrary choice becomes the next agent's evidence and can compound toward agreement. By analogy with neutral evolution, we call this sampling-driven regime memetic drift. QSG predicts a crossover from a drift-dominated regime, where consensus is effectively a lottery, to a selection regime, where weak biases are amplified and shape the outcome. We derive scaling laws for drift-induced polarization as a function of population size, communication bandwidth, in-context adaptation rate, and agents' internal uncertainty, and we validate them in both QSG simulations and naming-game experiments with LLM populations. Together, these results provide a framework for studying the collective mechanisms of social representation formation in multi-agent systems.

Hidenori Tanaka

CBS–NTT Program in Physics of Intelligence, Center for Brain Science, Harvard University · Physics of Artificial Intelligence Group, NTT Research, Inc.

Multi-Agent SystemsMulti-Agent ConsensusEmergent Behavior in Multi-Agent SystemsLarge Language Model-Based Social SimulationMulti-Agent Communication
AskPDF
Mar 23, 2026

More Isn't Always Better: Balancing Decision Accuracy and Conformity Pressures in Multi-AI Advice

Just as people improve decision-making by consulting diverse human advisors, they can now also consult with multiple AI systems. Prior work on group decision-making shows that advice aggregation creates pressure to conform, leading to overreliance. However, the conditions under which multi-AI consultation improves or undermines human decision-making remain unclear. We conducted experiments with three tasks in which participants received advice from panels of AIs. We varied panel size, within-panel consensus, and the human-likeness of presentation. Accuracy improved for small panels relative to a single AI; larger panels yielded no gains. The level of within-panel consensus affected participants' reliance on AI advice: High consensus fostered overreliance; a single dissent reduced pressure to conform; wide disagreement created confusion and undermined appropriate reliance. Human-like presentations increased perceived usefulness and agency in certain tasks, without raising conformity pressure. These findings yield design implications for presenting multi-AI advice that preserve accuracy while mitigating conformity.

Yuta Tsuchiya, Yukino Baba

The University of Tokyo Tokyo, Japan

Human-AI Decision MakingMulti-Agent Consensus
AskPDF
Mar 23, 2026

MIND: Multi-agent inference for negotiation dialogue in travel planning

While Multi-Agent Debate (MAD) research has advanced, its efficacy in coordinating complex stakeholder interests such as travel planning remains largely unexplored. To bridge this gap, we propose MIND (Multi-agent Inference for Negotiation Dialogue), a framework designed to simulate realistic consensus-building among travelers with heterogeneous preferences. Grounded in the Theory of Mind (ToM), MIND introduces a Strategic Appraisal phase that infers opponent willingness (w) from linguistic nuances with 90.2% accuracy. Experimental results demonstrate that MIND outperforms traditional MAD frameworks, achieving a 20.5% improvement in High-w Hit and a 30.7% increase in Debate Hit-Rate, effectively prioritizing high-stakes constraints. Furthermore, qualitative evaluations via LLM-as-a-Judge confirm that MIND surpasses baselines in Rationality (68.8%) and Fluency (72.4%), securing an overall win rate of 68.3%. These findings validate that MIND effectively models human negotiation dynamics to derive persuasive consensus.

Hunmin Do, Taejun Yoon, Kiyong Jung

School of Mechanical Engineering, Sungkyunkwan University, Suwon, Korea · Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul, Korea · Department of Software, Sungkyunkwan University, Suwon, Korea

Travel PlanningMulti-Agent NegotiationMulti-Agent ConsensusMulti-Agent DebateLLM Planning
AskPDF
Mar 14, 2026

Non-trivial consensus on directed signed matrix-weighted networks with compound measurement noises and time-varying topologies

This paper studies non-trivial consensus--a relatively novel and unexplored convergence behavior--on directed signed matrix-weighted networks subject to both additive and multiplicative measurement noises under time-varying topologies. Building upon grounded matrix-weighted Laplacian properties, a stochastic dynamic model is established that simultaneously captures inter-dimensional cooperative and antagonistic interactions, compound measurement noises and time-varying network structures. Based on stochastic differential equations theory, protocols that guarantee mean square and almost sure non-trivial consensus are proposed. Specifically, for any predetermined non-trivial consensus state, all agents are proven to converge toward this non-zero value in the mean-square and almost-sure senses. The design of control gain function in our protocols highlights a balanced consideration of the cumulative effect over time, the asymptotic decay property and the finite energy corresponding to measurement noises. Notably, the conditions on time-varying topologies in our protocols only require boundedness of elements in edge weight matrices, which facilitate the practicality of concept "time-varying topology" in matrix-weighted network consensus algorithms. Furthermore, the proposed protocols operate under milder connectivity conditions and no requirements on structural (un)balance properties. The work in this paper demonstrates that groups with both cooperative and antagonistic inter-dimensional interactions can achieve consensus even in the presence of compound measurement noises and time-varying topologies, challenging the conventional belief that consensus is attainable only in fully cooperative settings.

Tianmu Niu, Xiaoqun Wu

School of Mathematics and Statistics, Wuhan University, Wuhan, 430072, China · College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China

Multi-Agent Consensus
AskPDF
Mar 13, 2026

Semantic Consensus: Process-Aware Conflict Detection and Resolution for Enterprise Multi-Agent LLM Systems

Multi-agent large language model (LLM) systems are rapidly emerging as the dominant architecture for enterprise AI automation, yet production deployments exhibit failure rates between 41% and 86.7%, with nearly 79% of failures originating from specification and coordination issues rather than model capability limitations. This paper identifies Semantic Intent Divergence--the phenomenon whereby cooperating LLM agents develop inconsistent interpretations of shared objectives due to siloed context and absent process models--as a primary yet formally unaddressed root cause of multi-agent failure in enterprise settings. We propose the Semantic Consensus Framework (SCF), a process-aware middleware comprising six components: a Process Context Layer for shared operational semantics, a Semantic Intent Graph for formal intent representation, a Conflict Detection Engine for real-time identification of contradictory, contention-based, and causally invalid intent combinations, a Consensus Resolution Protocol using a policy--authority--temporal hierarchy, a Drift Monitor for detecting gradual semantic divergence, and a Process-Aware Governance Integration layer for organizational policy enforcement. Evaluation across 600 runs spanning three multi-agent frameworks (AutoGen, CrewAI, LangGraph) and four enterprise scenarios demonstrates that SCF is the only approach to achieve 100% workflow completion--compared to 25.1% for the next-best baseline--while detecting 65.2% of semantic conflicts with 27.9% precision and providing complete governance audit trails. The framework is protocol-agnostic and compatible with MCP and A2A communication standards.

Vivek Acharya

Independent Researcher, Dallas, TX, USA

Multi-Agent CoordinationMulti-Agent ConsensusAI Agent Governance
AskPDF
Mar 11, 2026

Distributed Kalman--Consensus Filtering with Adaptive Uncertainty Weighting for Multi-Object Tracking in Mobile Robot Networks

This paper presents an implementation and evaluation of a Distributed Kalman--Consensus Filter (DKCF) for Multi-Object Tracking (MOT) in mobile robot networks operating under partial observability and heterogeneous localization uncertainty. A key challenge in such systems is the fusion of information from agents with differing localization quality, where frame misalignment can lead to inconsistent estimates, track duplication, and ghost tracks. To address this issue, we build upon the MOTLEE framework and retain its frame-alignment methodology, which uses consistently tracked dynamic objects as transient landmarks to improve relative pose estimates between robots. On top of this framework, we propose an uncertainty-aware adaptive consensus weighting mechanism that dynamically adjusts the influence of neighbor information based on the covariance of the transmitted estimates, thereby reducing the impact of unreliable data during distributed fusion. Local tracking is performed using a Kalman Filter (KF) with a Constant Velocity Model (CVM) and Global Nearest Neighbor (GNN) data association. simulation results demonstrate that adaptive weighting effectively protects local estimates from inconsistent data, yielding a MOTA improvement of 0.09 for agents suffering from localization drift, although system performance remains constrained by communication latency.

Niusha Khosravi, Rodrigo Ventura, Meysam Basiri

Instituto Superior Técnico University of Lisbon Lisbon, Portugal

Multi-Object TrackingMulti-Robot SystemsKalman FilteringMulti-Agent Consensus
AskPDF
Mar 10, 2026

Emotional Modulation in Swarm Decision Dynamics

Collective decision-making in biological and human groups often emerges from simple interaction rules that amplify minor differences into consensus. The bee equation, developed initially to describe nest-site selection in honeybee swarms, captures this dynamic through recruitment and inhibition processes. Here, we extend the bee equation into an agent-based model in which emotional valence (positive-negative) and arousal (low-high) act as modulators of interaction rates, effectively altering the recruitment and cross-inhibition parameters. Agents display simulated facial expressions mapped from their valence-arousal states, allowing the study of emotional contagion in consensus formation. Three scenarios are explored: (1) the joint effect of valence and arousal on consensus outcomes and speed, (2) the role of arousal in breaking ties when valence is matched, and (3) the "snowball effect" in which consensus accelerates after surpassing intermediate support thresholds. Results show that emotional modulation can bias decision outcomes and alter convergence times by shifting effective recruitment and inhibition rates. At the same time, intrinsic non-linear amplification can produce decisive wins even in fully symmetric emotional conditions. These findings link classical swarm decision theory with affective and social modelling, highlighting how both emotional asymmetries and structural tipping points shape collective outcomes. The proposed framework offers a flexible tool for studying the emotional dimensions of collective choice in both natural and artificial systems.

David Freire-Obregón

SIANI, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain

Multi-Agent ConsensusMulti-Agent SystemsValence-Arousal ModelingAgent-Based Modeling
AskPDF
Mar 6, 2026

Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy

Multi-Agent Debate (MAD) has emerged as a promising paradigm for enhancing large language model reasoning. However, recent work reveals a limitation:standard MAD cannot improve belief correctness beyond majority voting; we refer to this as the Martingale Curse. This curse arises because correlated errors cause agents to converge toward erroneous consensus, where debate merely reinforces collective mistakes rather than filtering noise. We propose AceMAD, a framework that breaks the Martingale Curse by harnessing asymmetric cognitive potential energy to transform MAD from a random walk into a directed convergence process with positive drift. Through a peer-prediction mechanism, agents predict their peers' belief distributions, revealing asymmetric cognitive potential: truth-holders not only know the correct answer but also anticipate the crowd's misconceptions, while the hallucinating majority remains blind to their collective error. This asymmetry creates a potential energy gap that we quantify via strictly proper scoring rules. We prove this cognitive potential manifests as information-theoretic superiority and, under nonlinear aggregation, converts into submartingale drift toward truth, directly breaking the Martingale Curse. Experiments on challenging subsets across six benchmarks show AceMAD recovers sparse truth signals even when initial majorities are incorrect, substantially outperforming baseline methods.

Yuhan Liu, Juntian Zhang, Yichen Wu +4

Mohamed bin Zayed University of Artificial Intelligence · Gaoling School of Artificial Intelligence, Renmin University of China · Harvard University

Multi-Agent DebateMulti-Agent Consensus
AskPDF
Mar 6, 2026

Wisdom of the AI Crowd (AI-CROWD) for Ground Truth Approximation in Content Analysis: A Research Protocol & Validation Using Eleven Large Language Models

Large-scale content analysis is increasingly limited by the absence of observable ground truth or gold-standard labels, as creating such benchmarks through extensive human coding becomes impractical for massive datasets due to high time, cost, and consistency challenges. To overcome this barrier, we introduce the AI-CROWD protocol, which approximates ground truth by leveraging the collective outputs of an ensemble of large language models (LLMs). Rather than asserting that the resulting labels are true ground truth, the protocol generates a consensus-based approximation derived from convergent and divergent inferences across multiple models. By aggregating outputs via majority voting and interrogating agreement/disagreement patterns with diagnostic metrics, AI-CROWD identifies high-confidence classifications while flagging potential ambiguity or model-specific biases.

Luis de-Marcos, Manuel Goyanes, Adrián Domínguez-Díaz

Computer Science Department, Polytechnic School, University of Alcalá. Madrid, Spain. · MITCOM Research Group, Department of Communication, Carlos III University of Madrid, Spain

LLM-Assisted AnnotationLanguage Model EnsemblesMulti-Agent Consensus
AskPDF
Mar 4, 2026

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccuracies to gradually solidify into system-level false consensus through iteration. Such risks are difficult to trace since errors can propagate and amplify through message dependencies. Existing protections often rely on single-agent validation or require modifications to the collaboration architecture, which can weaken effective information flow and may not align with natural collaboration processes in real tasks. To address this, we propose a propagation dynamics model tailored for LLM-MAS that abstracts collaboration as a directed dependency graph and provides an early-stage risk criterion to characterize amplification risk. Through experiments on six mainstream frameworks, we identify three vulnerability classes: cascade amplification, topological sensitivity, and consensus inertia. We further instantiate an attack where injecting just a single atomic error seed leads to widespread failure. In response, we introduce a genealogy-graph-based governance layer, implemented as a message-layer plugin, that suppresses both endogenous and exogenous error amplification without altering the collaboration architecture. Experiments show that this approach prevents final infection in at least 89% of runs across operating modes and significantly mitigates the cascading spread of minor errors.

Yizhe Xie, Congcong Zhu, Xinyue Zhang +5

Faculty of Data Science, City University of Macau · Minzu University of China

Multi-Agent LLM SystemsMulti-Agent SystemsLLM Agent ReliabilityMulti-Agent System SecurityMulti-Agent Consensus
AskPDF
Mar 1, 2026

Can AI Agents Agree?

Large language models are increasingly deployed as cooperating agents, yet their behavior in adversarial consensus settings has not been systematically studied. We evaluate LLM-based agents on a Byzantine consensus game over scalar values using a synchronous all-to-all simulation. We test consensus in a no-stake setting where agents have no preferences over the final value, so evaluation focuses on agreement rather than value optimality. Across hundreds of simulations spanning model sizes, group sizes, and Byzantine fractions, we find that valid agreement is not reliable even in benign settings and degrades as group size grows. Introducing a small number of Byzantine agents further reduces success. Failures are dominated by loss of liveness, such as timeouts and stalled convergence, rather than subtle value corruption. Overall, the results suggest that reliable agreement is not yet a dependable emergent capability of current LLM-agent groups even in no-stake settings, raising caution for deployments that rely on robust coordination.

Frédéric Berdoz, Leonardo Rugli, Roger Wattenhofer

ETH Zurich, Switzerland

Multi-Agent ConsensusLLM Agent ReliabilityLLM Agent Evaluation
AskPDF
Feb 26, 2026

Decentralized Ranking Aggregation via Gossip: Convergence and Robustness

The concept of ranking aggregation plays a central role in preference analysis, and numerous algorithms for calculating median rankings, often originating in social choice theory, have been documented in the literature, offering theoretical guarantees in a centralized setting, i.e., when all the ranking data to be aggregated can be brought together in a single computing unit. For many technologies (e.g. peer-to-peer networks, IoT, multi-agent systems), extending the ability to calculate consensus rankings with guarantees of convergence and resilience to potential contamination in a decentralized setting, when preference data is initially distributed across a communicating network, remains a major methodological challenge. Indeed, in recent years, the literature on decentralized computation has mainly focused on computing or optimizing statistics such as arithmetic means using gossip algorithms. The purpose of this article is precisely to study how to achieve reliable and resilient consensus on collective rankings in a decentralized setting, thereby raising new questions, robustness to corrupted nodes, and scalability through reduced communication costs in particular. The approach proposed and analyzed here relies on the robustness guarantees offered by random gossip communication, which allows autonomous agents to compute a global ranking consensus using local interactions only, without coordination or a central authority.

Kerrian Le Caillec, Anna Van Elst, Igor Colin +1

LTCI, Télécom-Paris, Institut Polytechnique de Paris 19 Place Marguerite Perey, 91120 Palaiseau

Rank AggregationMulti-Agent Consensus
AskPDF
Feb 25, 2026

Epistemic Filtering and Collective Hallucination: A Jury Theorem for Confidence-Calibrated Agents

We investigate the collective accuracy of heterogeneous agents who learn to estimate their own reliability over time and selectively abstain from voting. While classical epistemic voting results, such as the Condorcet Jury Theorem (CJT), assume fixed participation, real-world aggregation often benefits from allowing agents to say ``I don't know.'' We propose a probabilistic framework where agents engage in a calibration phase, updating beliefs about their own fixed competence, before facing a final confidence gate that determines whether to vote or abstain. We derive a non-asymptotic lower bound on the group's success probability and prove that this selective participation generalizes the asymptotic guarantees of the CJT to a sequential, confidence-gated setting. Empirically, we validate these bounds via Monte Carlo simulations. While our results are general, we discuss their potential application to AI safety, outlining how this framework can mitigate hallucinations in collective LLM decision-making.

Jonas Karge

Technische Universität Dresden

Social Choice TheoryAI Agent ReliabilityMulti-Agent ConsensusProbability Calibration
AskPDF