# Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate

arXiv: https://arxiv.org/abs/2509.05396 · HTML: https://mlsanity.com/paper/2509.05396/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [A Survey of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2312.14925/) (2023)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [On scalable oversight with weak LLMs judging strong LLMs](https://mlsanity.com/paper/2407.04622/) (2024)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate](https://mlsanity.com/paper/2406.14711/) (2024)
- [ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2411.00053/) (2024)
- [LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning](https://mlsanity.com/paper/2502.05453/) (2025)
- [Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents](https://mlsanity.com/paper/2501.00430/) (2024)
- [When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)](https://mlsanity.com/paper/2504.00374/) (2025)

## Built on by (most cited first, 30 of 66)

- [Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate](https://mlsanity.com/paper/2509.23055/) (2025)
- [Demystifying Multi-Agent Debate: The Role of Confidence and Diversity](https://mlsanity.com/paper/2601.19921/) (2026)
- [The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation](https://mlsanity.com/paper/2511.02687/) (2025)
- [Reasoning Models Generate Societies of Thought](https://mlsanity.com/paper/2601.10825/) (2026)
- [AgentAsk: Multi-Agent Systems Need to Ask](https://mlsanity.com/paper/2510.07593/) (2025)
- [Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems](https://mlsanity.com/paper/2603.00131/) (2026)
- [The Illusion of Multi-Agent Advantage](https://mlsanity.com/paper/2606.13003/) (2026)
- [On the Reliability Limits of LLM-Based Multi-Agent Planning](https://mlsanity.com/paper/2603.26993/) (2026)
- [Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation](https://mlsanity.com/paper/2604.18005/) (2026)
- [Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate](https://mlsanity.com/paper/2606.00820/) (2026)
- [Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation](https://mlsanity.com/paper/2601.21464/) (2026)
- [Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems](https://mlsanity.com/paper/2604.02668/) (2026)
- [Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration](https://mlsanity.com/paper/2511.19417/) (2025)
- [DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation](https://mlsanity.com/paper/2601.05746/) (2026)
- [Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning](https://mlsanity.com/paper/2603.01221/) (2026)
- [Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring](https://mlsanity.com/paper/2603.27404/) (2026)
- [When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?](https://mlsanity.com/paper/2510.20963/) (2025)
- [Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement](https://mlsanity.com/paper/2606.27409/) (2026)
- [Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents](https://mlsanity.com/paper/2510.14453/) (2025)
- [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://mlsanity.com/paper/2605.08647/) (2026)
- [Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy](https://mlsanity.com/paper/2605.12991/) (2026)
- [The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size](https://mlsanity.com/paper/2606.02646/) (2026)
- [SLMJury: Can Small Language Models Judge as Well as Large Ones?](https://mlsanity.com/paper/2606.07810/) (2026)
- [Reliable agent engineering should integrate machine-compatible organizational principles](https://mlsanity.com/paper/2512.07665/) (2025)
- [The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate](https://mlsanity.com/paper/2605.00914/) (2026)
- [Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2605.03310/) (2026)
- [Flag Game: A Toy Model for Mechanistic Swarm Interpretability](https://mlsanity.com/paper/2609.19124/) (2026)
- [Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration](https://mlsanity.com/paper/2509.21848/) (2025)
- [Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives](https://mlsanity.com/paper/2511.08710/) (2025)
- [M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities](https://mlsanity.com/paper/2601.02854/) (2026)

## Abstract (arXiv)

While multi-agent debate has been proposed as a promising strategy for improving AI reasoning ability, we find that debate can sometimes be harmful rather than helpful. Prior work has primarily focused on debates within homogeneous groups of agents, whereas we explore how diversity in model capabilities influences the dynamics and outcomes of multi-agent interactions. Through a series of experiments, we demonstrate that debate can lead to a decrease in accuracy over time - even in settings where stronger (i.e., more capable) models outnumber their weaker counterparts. Our analysis reveals that models frequently shift from correct to incorrect answers in response to peer reasoning, favoring agreement over challenging flawed reasoning. We perform additional experiments investigating various potential contributing factors to these harmful shifts - including sycophancy, social conformity, and model and task type. These results highlight important failure modes in the exchange of reasons during multi-agent debate, suggesting that naive applications of debate may cause performance degradation when agents are neither incentivised nor adequately equipped to resist persuasive but incorrect reasoning.