Multi-agent discussion gains less when dissent is withheld

arXiv:2609.38324 · physics.soc-ph, cs.CL, cs.MA · Submitted 2026-09-29 · Read on arXiv

physics.soc-ph, cs.CL, cs.MA

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/skojaku/multi-agent-discussion-withholding

Terminology

• Benchmark — 42× in this paper · explained in 2 episodes
• Accuracy — 30× in this paper · explained in 1 episode
• Multi-Agent System — 6× in this paper · explained in 6 episodes
• Generative AI — 5× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 4× in this paper
• Bayesian Inference — 3× in this paper · explained in 5 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• In Conference on Language Modeling — 2× in this paper
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Sycophancy — 2× in this paper · explained in 4 episodes
• Agent-Based Simulation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cooperation — 1× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• In Forty-third International Conference on Machine Learning — 1× in this paper
• Interpretability — 1× in this paper · explained in 15 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Phase Transitions — 1× in this paper · explained in 2 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Systematic Bias — 1× in this paper · explained in 3 episodes
• Universality Class — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Conformity Generates Collective Misalignment in AI Agents Societies
• Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics
• Improving Factuality and Reasoning in Language Models through Multiagent Debate
• Message capacity and claim wording set the transition points of collective truth-finding in language-model networks
• What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
• Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
• Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
• When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs
• LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
• Flag Game: A Toy Model for Mechanistic Swarm Interpretability
• The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
• Towards Understanding Sycophancy in Language Models
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
• Everyone Conforms, No One Believes: Pluralistic Ignorance in LLM Agent Populations
• Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity

Related papers

• URBAN-SPIN: A street-level bikeability index to inform design implementations in historical city centres
• Civilizational Metamaterials: Engineering Coordination Under Capability Gradients and Structural Turbulence
• Collective Behavior of AI Agents: the Case of Moltbook
• A Distinct Communication Strategies Model of the Double Empathy Problem
• Measuring Primitive Accumulation: An Information-Theoretic Approach to Capitalist Enclosure in PIK2, Indonesia
• Diffusion-induced instabilities promote cooperation in eco-evolutionary networks