# Free-MAD: Consensus-Free Multi-Agent Debate

arXiv: https://arxiv.org/abs/2509.11035 · HTML: https://mlsanity.com/paper/2509.11035/

## Key facts

- Cited by 29 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 55 references that are in the map.
- First posted on arXiv 14 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, 30 of 41)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [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)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents](https://mlsanity.com/paper/2503.00061/) (2025)
- [Red-Teaming LLM Multi-Agent Systems via Communication Attacks](https://mlsanity.com/paper/2502.14847/) (2025)
- [Improving Multi-Agent Debate with Sparse Communication Topology](https://mlsanity.com/paper/2406.11776/) (2024)
- [Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://mlsanity.com/paper/2305.11595/) (2023)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification](https://mlsanity.com/paper/2407.20859/) (2024)
- [Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration](https://mlsanity.com/paper/2310.00280/) (2023)
- [Do as We Do, Not as You Think: the Conformity of Large Language Models](https://mlsanity.com/paper/2501.13381/) (2025)
- [SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution](https://mlsanity.com/paper/2507.23348/) (2025)
- [A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions](https://mlsanity.com/paper/2406.03712/) (2024)
- [Conformity in Large Language Models](https://mlsanity.com/paper/2410.12428/) (2024)
- [Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System](https://mlsanity.com/paper/2312.04854/) (2023)
- [Citation-Enhanced Generation for LLM-based Chatbots](https://mlsanity.com/paper/2402.16063/) (2024)
- [Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges](https://mlsanity.com/paper/2502.08680/) (2025)

## Built on by (most cited first, 29 of 29)

- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [Toward Efficient Agents: Memory, Tool learning, and Planning](https://mlsanity.com/paper/2601.14192/) (2026)
- [StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management](https://mlsanity.com/paper/2601.05890/) (2026)
- [When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2608.03421/) (2026)
- [Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval](https://mlsanity.com/paper/2601.04742/) (2026)
- [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://mlsanity.com/paper/2605.08647/) (2026)
- [HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate](https://mlsanity.com/paper/2604.09679/) (2026)
- [To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG](https://mlsanity.com/paper/2606.25191/) (2026)
- [Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval](https://mlsanity.com/paper/2606.24976/) (2026)
- [Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning](https://mlsanity.com/paper/2608.02291/) (2026)
- [Harness-RL: Black-Box Reinforcement Learning with Action-Args Decoupling for Central-Agent Multi-Agent Harnesses](https://mlsanity.com/paper/2608.29641/) (2026)
- [Multi-agent decision making: A Blackwell's informativeness approach](https://mlsanity.com/paper/2605.06028/) (2026)
- [AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization](https://mlsanity.com/paper/2605.08704/) (2026)
- [You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents](https://mlsanity.com/paper/2605.27586/) (2026)
- [Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents](https://mlsanity.com/paper/2607.15095/) (2026)
- [Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering](https://mlsanity.com/paper/2608.01463/) (2026)
- [Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate](https://mlsanity.com/paper/2608.03648/) (2026)
- [When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Diagnostic for Machine Collectives](https://mlsanity.com/paper/2608.03722/) (2026)
- [Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique](https://mlsanity.com/paper/2608.20777/) (2026)
- [Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognition](https://mlsanity.com/paper/2608.23029/) (2026)
- [Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation](https://mlsanity.com/paper/2609.03619/) (2026)
- [Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate](https://mlsanity.com/paper/2609.27150/) (2026)
- [BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation](https://mlsanity.com/paper/2609.35551/) (2026)
- [MADBench: Benchmarking the Security of Multi-Agent Debate](https://mlsanity.com/paper/2609.39146/) (2026)
- [MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate](https://mlsanity.com/paper/2609.39297/) (2026)
- [Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems](https://mlsanity.com/paper/2610.01042/) (2026)
- [Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries](https://mlsanity.com/paper/2610.02005/) (2026)
- [Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems](https://mlsanity.com/paper/2610.08901/) (2026)
- [Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate](https://mlsanity.com/paper/2610.18240/) (2026)

## Abstract (arXiv)

Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is selected by majority voting in the last round. However, this consensus-based design faces several limitations. First, multiple rounds of communication increases token overhead and limits scalability. Second, due to the inherent conformity of LLMs, agents that initially produce correct responses may be influenced by incorrect ones during the debate process, causing error propagation. Third, majority voting introduces randomness and unfairness in the decision-making phase, and can degrade the reasoning performance. To address these issues, we propose textscFree-MAD, a novel MAD framework that eliminates the need for consensus among agents. textscFree-MAD introduces a novel score-based decision mechanism that evaluates the entire debate trajectory rather than relying on the last round only. This mechanism tracks how each agent's reasoning evolves, enabling more accurate and fair outcomes. In addition, textscFree-MAD reconstructs the debate phase by introducing anti-conformity, a mechanism that enables agents to mitigate excessive influence from the majority. Experiments on eight benchmark datasets demonstrate that textscFree-MAD significantly improves reasoning performance while requiring only a single-round debate and thus reducing token costs. We also show that compared to existing MAD approaches, textscFree-MAD exhibits improved robustness in real-world attack scenarios.