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

May 13, 2026cs.LG

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy. We test this attribution across four model families and find it largely wrong: pretrained base models exhibit the same substitution pattern as their Instruct variants, averaging higher yield than Instruct. Using activation patching, we localize the corruption to a narrow mid-layer window where attention carries the causal weight and MLP contribution is negligible; patching above this window restores 96% of the clean-to-pressured P(correct) gap. The attack surface decomposes into two independent factors (channel framing and consensus strength) whose interaction produces a 47.5 percentage-point yield gap at majority consensus, preserved across jury sizes

N \in \{4, 5, 6\}

. Two converging activation-space interventions show that pressure suppresses clean-reasoning features rather than activating a new sycophancy circuit. A single correctly-arguing dissenter reduces yield by 54-73 percentage points across all framings tested, whereas the strongest prompt-level defense fails on attack variants outside its design surface. Mitigations should target the mechanism, structured dissent at the pipeline level, rather than prompt-level defenses.

Adarsh Kumarappan, Ananya Mujoo

1California Institute of Technology · 2Evergreen Valley College

AI Agent Reliability Multi-Agent LLM Systems LLM Sycophancy Adversarial Attacks on LLMs Multi-Agent Consensus Causal Interventions in Language Models

May 11, 2026cs.MA

Effect of Graph Gluing on Consensus in Networked Multi-Agent Systems

In this paper, the effects of graph gluing operations in networks of multi-agent systems and their impact on system performance are investigated. In many practical applications, multiple multi-agent subsystems must be interconnected through communication links to accomplish complex tasks, resulting in a larger communication network. Such interconnections modify the underlying graph topology and consequently affect the consensus behavior and convergence rate of the network. In particular, this paper examines both bridge gluing and interface gluing and analyzes how the number and structure of communication links between subsystems influence the Fiedler eigenvalue of the resulting graph. Since the Fiedler eigenvalue is directly related to the convergence rate of consensus dynamics, the proposed analysis establishes a clear relationship between interconnection strategies, algebraic connectivity, and system performance. The results provide theoretical insight into how different gluing mechanisms alter the spectral properties of the graph Laplacian and, in turn, the convergence characteristics of the networked multi-agent system. Simulation studies are presented to illustrate the theoretical findings and to validate the effectiveness of the proposed framework.

Rohollah Moghadam, Santosh Kandel

Department of Electrical and Electronic Engineering, California State University-Sacramento, 5028 Riverside Hall, 6000 J Street, Sacramento, CA, 95819, USA · Department of Mathematics and Statistics, California State University-Sacramento, 226 Brighton Hall, 6000 J Street, Sacramento, CA, 95819, USA

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

May 9, 2026cs.MA

Robust Multi-Agent LLMs under Byzantine Faults

Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also become a source of vulnerability, as unreliable or Byzantine agents may sway neighboring agents toward incorrect conclusions and degrade overall system performance. Existing methods rely on leader-based coordination or self-reported confidence, both of which are susceptible to adversarial manipulation. We study decentralized LLM multi-agent systems (LLM-MAS) and propose Self-Anchored Consensus (SAC), a fully decentralized iterative filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs. We present

(F{+}1)

-robustness conditions for the communication graph that ensure honest agents preserve and propagate reliable information despite Byzantine influence. Experiments on mathematical and commonsense reasoning benchmarks show that SAC effectively suppresses Byzantine influence and consistently improves performance across diverse communication topologies, whereas prior methods degrade under adversarial conditions.

Haejoon Lee, Vincent-Daniel Yun, Dimitra Panagou +1

Department of Robotics, University of Michigan, Ann Arbor, USA · Thomas Lord Department of Computer Science, University of Southern California, USA

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

May 8, 2026cs.MA

Insider Attacks in Multi-Agent LLM Consensus Systems

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange messages and update decisions to reach a shared outcome. However, most existing multi-agent LLM frameworks assume that all participating agents are aligned with the system objective. In practice, a malicious insider may participate as a legitimate member of the group while pursuing a hidden adversarial goal. In this work, we study insider manipulation in multi-agent LLM consensus systems. We formalize the problem as a sequential decision-making task in which a malicious agent seeks to delay or prevent agreement among benign agents. To make attack optimization tractable, we propose a world-model-based framework that learns surrogate dynamics over the latent behavioral states of benign agents and then trains an attacker using reinforcement learning based on this learned model. Preliminary results show that the trained attacker reduces the benign consensus rate and prolongs disagreement more effectively than the direct malicious-prompt baseline. These results suggest that combining latent world models with reinforcement learning is a promising direction for adaptive insider attacks in language-based multi-agent systems.

Xiaolin Sun, Zixuan Liu, Yibin Hu +1

Department of Computer Science, Tulane University, New Orleans, United States of America.

Multi-Agent LLM Systems Multi-Agent Systems Multi-Agent Consensus Multi-Agent System Security

May 7, 2026cs.MA

The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search

Distributed agents in real-world settings frequently must coordinate under uncertainty with only partial observations. Coordination is necessary to share beliefs to aid in task completion, but communication costs bandwidth, introduces latency, and if done poorly, can degrade collective reasoning. This tension is especially acute in bandwidth-constrained deployments such as distributed sensing networks, autonomous reconnaissance, and collaborative cyber defense, where excessive transmission carries direct operational costs. Existing work has focused on multi-agent exploration and communication strategies, but not on how communication frequency and content jointly shape the collective belief state. Central to this challenge is the degree to which agents maintain compatible internal beliefs about the environment, a property we term \textit{epistemic alignment}. When agents share beliefs effectively, they converge on correct hypotheses; when communication is poorly designed, agents may converge confidently on wrong ones. We formalize this distinction and show it is not detectable from coordination metrics alone such as Jensen-Shannon Divergence or rate to consensus.

David Farr, Iain Cruickshank, Kate Starbird +1

1*Information School, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA. · 2Computer Science, Carnegie Mellon University, 5000 Forbes Avenue,2026 Pittsburgh, 15213, PA, USA. · 3Human Centered Design Engineering, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA. +1

Opinion Dynamics Multi-Agent Systems Multi-Agent Consensus Multi-Agent Communication

May 5, 2026cs.LG

Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals

Large Language Model ensembles improve reasoning accuracy, but only up to a performance boundary beyond which additional deliberation degrades accuracy. We introduce DASE (Deliberative Adaptive Stopping Ensemble), a stopping heuristic for iterative ensemble deliberation that commits early on genuine consensus and applies a global-frequency fallback on fragmented evidence. We make three contributions. (1) DASE produces a commit-type routing partition that generalises across benchmarks and is complementary to verbalized single-call confidence. On GPQA-Extended (N=546, 70B ensemble), the partition yields a 39.5 pp routing gap (right-wall 81.1% vs. left-wall 41.5%). On AIME 2010-2023 (N=261, 120B ensemble, 3 seeds), right-wall commits reach 98.3% accuracy vs. left-wall 72.8% (25.5 pp gap), statistically equivalent to Opus 4.6 Standard verbalized confidence at matched coverage (25.7 pp gap; bootstrap p=0.873); the two mechanisms disagree on 37% of routing assignments. (2) Adaptive stopping, not injection bandwidth, drives accuracy. On AIME-300, bandwidth accounts for only 0.3 pp (ns). On GPQA-Extended at the 120B tier, sparse injection (

\approx15

tokens/worker/round) achieves 70.9% with a 30.7 pp routing gap; dense injection (

\approx600

chars/worker/round) achieves 72.2% but with halved right-wall coverage and a narrower 18.9 pp gap. (3) Injection-based methods exhibit an inverted-U accuracy-vs-inference trajectory; this pattern is hypothesis-generating.

Roberto E. Medina

Independent Researcher

LLM Inference Efficiency Multi-Agent Consensus LLM Routing Language Model Ensembles

May 1, 2026cs.MA

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 Optimization Multi-Agent Coordination Black-Box Optimization Distributed Optimization Large Language Model-Guided Optimization Multi-Agent Consensus

Apr 30, 2026cs.AI

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

Apr 29, 2026cs.MA

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

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

N{=}10

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

R{=}3

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

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

) and sampling temperature (

T \in \{0.4, 0.7\}

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

K{=}2

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

\times

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

Blaž Bertalanič, Carolina Fortuna

Jožef Stefan Institute Ljubljana, Slovenia

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

Apr 29, 2026cs.MA

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

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

Ariel Sela

Tel Aviv University

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

Apr 21, 2026cs.MA

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 Coordination Multi-Agent Collaboration Multi-Agent Consensus Human-AI Collaboration

Apr 18, 2026cs.CL

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 Systems Adversarial Robustness Multi-Agent Consensus Multi-Agent Reasoning

Feb 10, 2026cs.AI

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.

Wei Yang, Shixuan Li, Heng Ping +3

University of Southern California

LLM Auditing Preference Optimization Multi-Agent Systems Multi-Agent Consensus Multi-Agent Reasoning Reasoning Verification

Jan 20, 2026physics.soc-ph

Generating consensus and dissent on massive discussion platforms with a semantic-vector model

Reaching consensus on massive discussion networks is critical for reducing noise and achieving optimal collective outcomes. However, the natural tendency of humans to preserve their initial ideas constrains the emergence of global solutions. To address this, Collective Intelligence (CI) platforms facilitate the discovery of globally superior solutions. We introduce a dynamical system based on the standard

O(N)

model to drive the aggregation of semantically similar ideas. The system consists of users represented as nodes in a

d=2

lattice with nearest-neighbor interactions, where their ideas are represented by semantic vectors computed with a pretrained embedding model. We analyze the system's equilibrium states as a function of the coupling parameter

β

. Our results show that

β> 0

drives the system toward a ferromagnetic-like phase (global consensus), while

β< 0

induces an antiferromagnetic-like state (maximum dissent), where users maximize semantic distance from their neighbors. This framework offers a controllable method for managing the tradeoff between cohesion and diversity in CI platforms.

A. Ferrer, D. Muñoz-Jordán, A. Rivero +3

Instituto de Biocomputación y Física de Sistemas Complejos (BIFI), Universidad de Zaragoza, 50018 Zaragoza, Spain · Kampal Data Solutions, WTCZ, Avda. Maria Zambrano 31, 50018 Zaragoza, Spain · Departamento de Física Teórica, Universidad de Zaragoza, 50009 Zaragoza, Spain +2

Opinion Dynamics Computational Social Science Multi-Agent Consensus

Aug 24, 2025cs.GT

The price of uncertainty for social consensus

How hard is it to achieve consensus in a social network under uncertainty? In this paper we model this problem as a social graph of agents where each vertex is initially colored red or blue. The goal of the agents is to achieve consensus, which is when the colors of all agents align. Agents attempt to do this locally through steps in which an agent changes their color to the color of the majority of their neighbors. In real life, agents may not know exactly how many of their neighbors are red or blue, which introduces uncertainty into this process. Modeling uncertainty as perturbations of relative magnitude

1+\varepsilon

to these color neighbor counts, we show that even small values of

\varepsilon

greatly hinder the ability to achieve consensus in a social network. We prove theoretically tight upper and lower bounds on the price of uncertainty, a metric defined in previous work by Balcan et al. to quantify the effect of uncertainty in network games.

Yunzhe Bai, Alec Sun

Opinion Dynamics Multi-Agent Consensus Decision-Making under Uncertainty