Multi-Agent Consensus

Follow this topic Ask about this topic

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

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

Network Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations
Oct 24, 2026Sahil Rajesh DhayalkarMulti-Agent Consensus Belief Updating in LLMs
Arizona State University
Understanding Communication Failures in Multi-Agent LLM Systems
Oct 23, 2026Priya Pitre, Jun Hou, Yi Fang +2Multi-Agent LLM Systems Multi-Agent Communication
Virginia Tech, Blacksburg, VA 24061, USA
Network topology shapes consensus and vulnerability in LLM populations
Oct 22, 2026Roberto Passaro, Ariel Flint, Romualdo Pastor-Satorras +2Multi-Agent Consensus Multi-Agent Communication Topology
IT University of Copenhagen, Denmark. · Pioneer Centre for AI, Copenhagen, Denmark. · Department of Mathematics, City St George’s, University of London, UK. +1
Who Is the Influencer? Consensus Dynamics in Multi-Agent Systems
Oct 22, 2026Gouki Minegishi, Jingyuan Feng, Hiroki Furuta +3Multi-Agent LLM Systems Multi-Agent Consensus
The University of Tokyo
Seeing the Forest for the Trees: Emergent Agreement from Individual Conversations
Oct 21, 2026Adi Simhi, Yaniv Nikankin, Jonathan Herzig +3Multi-Agent Consensus Multi-Agent LLM Systems
Technion – Israel Institute of Technology · Google Research · University of Edinburgh
Measuring Consensus in AI Agent Networks
Oct 17, 2026Jin GaoMulti-Agent Consensus Multi-Agent Systems
Independent Researcher, USA
Train Locally, Learn Together: Distributed Multi-Agent Training via ADMM
Oct 17, 2026Yiwei Chen, Changsheng Wang, Yicheng Lang +3Distributed Training Multi-Agent Consensus
Michigan State University · University of Michigan, Ann Arbor
FRACTAL: A Self-Similar Multi-Agent Orchestration Architecture with Formal Communication, Convergence, and Depth Bounds
Oct 15, 2026Ohad Dan, Abhinav TaliyanMulti-Agent Orchestration AI Agent Architecture
Drivers of LLM Consensus Formation Under Competing Incentives: A Simulation Study
Oct 14, 2026Isabel Jones, Matthew Edwards, Janina A. HoffmannMulti-Agent Consensus Multi-Agent LLM Systems
University of Bristol Bristol, United Kingdom · University of Bath Bath, United Kingdom
Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
Oct 13, 2026Dezheng Bao, Sihang Du, Renhong Huang +3Multi-Agent Debate Multi-Agent Reasoning
Zhejiang University
ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning
Oct 13, 2026Yuan Liu, Haoyue Peng, Fanliang Hu +2Multi-Agent Reasoning LLM Agent Reliability
Medical Artificial Intelligence Laboratory, Chongqing University Cancer Hospital, Chongqing University, Chongqing 400030, China
GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines
Oct 12, 2026Yuanfan Lin, Jie Di, Xujin He +21Human-AI Collaboration Multi-Agent Consensus
Zhongshan Ophthalmic Center, Sun Yat-sen University, WHO Collaborating Centre for Eye Care and Vision, State Key Laboratory of Ophthalmology, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China · Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China · Hainan Eye Hospital and Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Haikou, Hainan, China +2
Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms
Oct 6, 2026Xiaoyang Wang, Tianrui Wang, Christopher C. YangLLM Abstention Selective Prediction
Drexel University · University of Michigan, Ann Arbor
Entropy-Gated Belief Coordination for Decentralized Multi-Agent Search Under Intermittent Communication
Oct 5, 2026Mohamed Abdelnaby, Kevin LeahyBelief-Space Planning Multi-Agent Coordination
Department of Robotics Engineering, Worcester Polytechnic Institute
Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise
Oct 2, 2026Ziang Ni, Peng ZouNormative Conformity in Language Models Multi-Agent Debate
Sun Yat-sen University Guangzhou, China
Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents
Oct 2, 2026Tathagata Banerjee, Nima MoghaddasEmergent Behavior in Multi-Agent Systems Large Language Model-Based Social Simulation
Northeastern University
Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries
Oct 1, 2026Ionel Eduard Stan, Paolo NapoletanoLanguage Model Calibration Computational Argumentation
Department of Informatics, Systems and Communication (DISCo), University of Milano–Bicocca, Milan, Italy
Consensus and Factual Dynamics in Large Populations of Interacting Language Models
Sep 30, 2026Emanuele Ricco, Elia Onofri, Vincenzo Sammartino +1Hallucination in Language Models Multi-Agent Consensus
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
Multi-agent discussion gains less when dissent is withheld
Sep 29, 2026Chand Sahil Mansuri, Xin Wang, Mengying Li +4Multi-Agent LLM Systems Opinion Dynamics
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
Bregman Consensus
Sep 28, 2026Andrei N. SoklakovFunctional Bregman Divergences Multi-Agent Consensus
LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems
Sep 27, 2026Liron Soffer, Ravid Shwartz-Ziv, Chen ShaniNormative Conformity in Language Models Social Bias in Language Models
Tel-Aviv University · New York University
Collective Regimes in Multi-Agent LLMs under Reasoning Effort and Communication Topology
Sep 27, 2026Machiko Hirota, Akshara Nadayanur Sathis Kanna, Ujwal Kumar +1Multi-Agent LLM Systems Multi-Agent Coordination
University of Pennsylvania · Carnegie Mellon University · Shibaura Institute of Technology
Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis
Sep 25, 2026Jakub Masłowski, Jarosław A. ChudziakMulti-Agent Consensus Multi-Agent Debate
Institute of Computer Science Warsaw University of Technology Warsaw, Poland
Reinforcement Learning of Communication in a Mesh of Small Language Models
Sep 24, 2026Mehmet Kerem TurkcanMulti-Agent Communication RL for LLM Agents
Department of Civil Engineering, Columbia University
Verification Pulses and the Cost of Escaping Wrong Consensus
Sep 24, 2026Shivam GuptaMulti-Agent Consensus
Independent Researcher
ZO-COSMO: Index-Free One-Hop Mixing for Decentralized Zeroth-Order Optimization
Sep 23, 2026Shengjun Zhang, Tingyi Liu, Heng Zhang +1Communication-Efficient Distributed Training Multi-Agent Consensus
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
Calibration Is Not Verification: Answer-Level Conformal Guarantees for Mixture-of-Agents
Sep 22, 2026Nada Rahali, Zijia Wang, Zhi-Song LiuFactual Consistency Evaluation Conformal Prediction
LUT University, Finland · Dell Technologies, United Kingdom · Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom
AC-DC: Adaptive Communication for Scalable Dynamic Average Consensus in Multi-Robot Ergodic Search
Sep 21, 2026Robin Inho Kee, Begum Cannataro, Vasileios TzoumasMulti-Robot Coordination Multi-Agent Consensus
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
The Wisdom of Artificial Deliberative Crowds
Sep 18, 2026Federico Barrera-Lemarchand, Mariano Sigman, Joaquin NavajasMulti-Agent Deliberation Multi-Agent Consensus
Laboratorio de Neurociencia, Escuela de Negocios, Universidad Torcuato Di Tella, Buenos Aires, Argentina · Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Buenos Aires, Argentina
Language-model groups overstate consensus when replaying human deliberation on a reasoning task
Sep 17, 2026Tengfei ShaoMulti-Agent LLM Systems LLM Agent Evaluation
Global Education Center, Waseda University, Tokyo, Japan

Oct 24, 2026J/K move · Enter open · S save

Network Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations

Sahil Rajesh Dhayalkar

Arizona State University

Multi-Agent Consensus Belief Updating in LLMs Large Language Model-Based Social Simulation Multi-Agent Communication Topology

Open paper AskPDF arXiv

As multi-agent language model networks become widely deployed, predicting their collective behavior is a critical challenge. Classical distributed consensus theory relies on network topology to predict convergence, structurally assuming that agent updates are convex combinations, population means are conserved, and weights are content-independent. In this work, we demonstrate that these foundational assumptions fail for large language models (LLMs). By deterministically extracting continuous credence from token-level probabilities across eight instruction-tuned models and 73,080 controlled exchanges, we directly measure the empirical LLM update operator. We find that LLMs systematically violate convexity by updating outside the hull of observed opinions, exhibiting active repulsion (negative weights) that fundamentally breaks row-stochastic modeling and standard bounded-confidence repairs. Scaling these empirically fitted operators to simulations of 10,000 agents reveals that algebraic connectivity explains almost none of the final outcome variance. Instead, population dynamics are governed entirely by the model's internal update bias and message framing. Consequently, populations of several models, including those with up to 7B parameters, reliably compound small local drifts to reach confident agreement on objectively false claims regardless of their network structure. Our results prove that classical graph-theoretic metrics are inadequate for LLM populations, highlighting a profound deployment risk where multi-agent deliberation predictably saturates in collective delusion.