# Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity

arXiv: https://arxiv.org/abs/2502.08788 · HTML: https://mlsanity.com/paper/2502.08788/

## Key facts

- Cited by 44 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 41 of its 46 references that are in the map.
- First posted on arXiv 12 Feb 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, 30 of 41)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [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)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)

## Built on by (most cited first, 30 of 44)

- [The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants](https://mlsanity.com/paper/2505.19797/) (2025)
- [MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks](https://mlsanity.com/paper/2505.12371/) (2025)
- [Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate](https://mlsanity.com/paper/2509.23055/) (2025)
- [Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning](https://mlsanity.com/paper/2511.07784/) (2025)
- [When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning](https://mlsanity.com/paper/2510.07517/) (2025)
- [Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute](https://mlsanity.com/paper/2504.00762/) (2025)
- [Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate](https://mlsanity.com/paper/2504.16489/) (2025)
- [iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference](https://mlsanity.com/paper/2511.11306/) (2025)
- [The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems](https://mlsanity.com/paper/2602.15382/) (2026)
- [IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2505.12442/) (2025)
- [Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate](https://mlsanity.com/paper/2606.00820/) (2026)
- [Scaling Discovery through Test-Time Communication](https://mlsanity.com/paper/2609.21032/) (2026)
- [Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation](https://mlsanity.com/paper/2601.21464/) (2026)
- [Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning](https://mlsanity.com/paper/2603.01221/) (2026)
- [Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate](https://mlsanity.com/paper/2510.10002/) (2025)
- [WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference](https://mlsanity.com/paper/2603.11132/) (2026)
- [The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence](https://mlsanity.com/paper/2605.16895/) (2026)
- [SLMJury: Can Small Language Models Judge as Well as Large Ones?](https://mlsanity.com/paper/2606.07810/) (2026)
- [The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment](https://mlsanity.com/paper/2606.08457/) (2026)
- [Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization](https://mlsanity.com/paper/2505.17115/) (2025)
- [HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate](https://mlsanity.com/paper/2604.09679/) (2026)
- [The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning](https://mlsanity.com/paper/2605.01704/) (2026)
- [PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion](https://mlsanity.com/paper/2508.06110/) (2025)
- [Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning](https://mlsanity.com/paper/2601.19151/) (2026)
- [Dynamic Coordination Strategy Selection for Enterprise Multi-Agent Systems](https://mlsanity.com/paper/2606.00804/) (2026)
- [Does Multi-Agent Debate Improve AI Feedback on Research Papers?](https://mlsanity.com/paper/2607.14713/) (2026)
- [AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions](https://mlsanity.com/paper/2608.03283/) (2026)
- [Self-Organizing Agent Teams Learn to Reason Together](https://mlsanity.com/paper/2609.22682/) (2026)
- [Adaptive Reasoning Executor: A Collaborative Agent System for Efficient Reasoning](https://mlsanity.com/paper/2510.13214/) (2025)
- [Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science](https://mlsanity.com/paper/2602.05289/) (2026)

## Abstract (arXiv)

Multi-agent debate (MAD) has gained significant attention as a promising line of research to improve the factual accuracy and reasoning capabilities of large language models (LLMs). Despite its conceptual appeal, current MAD research suffers from critical limitations in evaluation practices, including limited benchmark coverage, weak baseline comparisons, and inconsistent setups. This paper presents a systematic evaluation of 5 representative MAD methods across 9 benchmarks using 4 foundational models. Surprisingly, our findings reveal that MAD often fail to outperform simple single-agent baselines such as Chain-of-Thought and Self-Consistency, even when consuming significantly more inference-time computation. To advance MAD research, we further explore the role of model heterogeneity and find it as a universal antidote to consistently improve current MAD frameworks. Based on our findings, we argue that the field must stop overvaluing MAD in its current form; for true advancement, we must critically rethink evaluation paradigms and actively embrace model heterogeneity as a core design principle.