Multi-Agent Debate

Ask about this topic

Overview

Multi-agent debate examines whether language models can reason more reliably by proposing answers, sharing evidence, challenging peers, and revising judgments. Common approaches assign roles such as advocate, critic, and judge; use retrieval and structured evidence checks; or adapt who communicates and when debate stops. Researchers apply these methods to mathematics, question answering, fact-checking, and medical or legal decisions, but results vary across tasks and model groups. A central tension is that debate can uncover errors when agents contribute useful independent information, yet consensus can also spread mistakes, suppress dissent, and add substantial cost.

Latest papers

CardsList

144 papers19 papers in the last four weeks, up 6% on the four weeks before. 0.1% of all new papers.

  1. From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation

    Apr 9, 2026Mengdie Flora Wang, Haochen Xie, Guanghui Wang +9LLM Agent SafetySelective Prediction

    AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China

  2. Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation

    Apr 8, 2026Philipp D. SiedlerPersuasion in Language ModelsMulti-Agent Systems

    Aleph Alpha Research, Heidelberg, Germany

  3. HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate

    Apr 3, 2026Yiqing Liu, Hantao Yao, Wu Liu +2Multi-Agent DebateMulti-Agent Reasoning

    University of Science and Technology of China

  4. Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification

    Mar 30, 2026Masnun Nuha Chowdhury, Nusrat Jahan Beg, Umme Hunny Khan +3Claim VerificationMulti-Agent Debate

    Systems and Software Lab (SSL), Department of Computer Science and Engineering, Islamic University of Technology, Dhaka, Bangladesh

  5. Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language Learning

    Mar 29, 2026Nicy Scaria, Silvester John Joseph Kennedy, Deepak SubramaniMulti-Agent DebateAutomated Evaluation

    Indian Institute of Science, India · Talking Yak, India · Indian Institute of Technology Patna, India

  6. Sci-Mind: Cognitively-Inspired Adversarial Debate for Autonomous Mathematical Modeling

    Mar 29, 2026Junhao Jia, Huangwei Chen, Ruiying Sun +4Autonomous Research AgentsLLM Mathematical Reasoning

    Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Science and Technology, Zhejiang University, China · Hangzhou Dianzi University, China · Hangzhou Normal University, China

  7. Multi-Agent Dialectical Refinement for Enhanced Argument Classification

    Mar 29, 2026Jakub Bąba, Jarosław A. ChudziakArgument MiningComputational Argumentation

    Faculty of Electronics and Information Technology, Warsaw University of Technology, Poland

  8. Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring

    Mar 28, 2026Jakub Masłowski, Jarosław A. ChudziakMulti-Agent DebateIntelligent Tutoring Systems

    Institute of Computer Science, Warsaw University of Technology, Poland

  9. The impact of multi-agent debate protocols on debate quality: a controlled case study

    Mar 28, 2026Ramtin Zargari MarandiMulti-Agent DebateMulti-Agent Communication

  10. MediHive: A Decentralized Agent Collective for Medical Reasoning

    Mar 28, 2026Xiaoyang Wang, Christopher C. YangMulti-Agent LLM SystemsMedical QA

    College of Computing and Informatics, Drexel University, Philadelphia, PA 19104, USA

  11. Emergent Collaborative Deliberation in Multi-Model AI Systems: A BFT-Derived Protocol for Epistemic Synthesis

    Mar 26, 2026VD DoskeMulti-Agent DebateMulti-Agent Consensus

    Independent Researcher / Consilia

  12. MIND: Multi-agent inference for negotiation dialogue in travel planning

    Mar 23, 2026Hunmin Do, Taejun Yoon, Kiyong JungTravel PlanningMulti-Agent Negotiation

    School of Mechanical Engineering, Sungkyunkwan University, Suwon, Korea · Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul, Korea · Department of Software, Sungkyunkwan University, Suwon, Korea

  13. Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention

    Mar 21, 2026Manh Nguyen, Anh Nguyen, Dung Nguyen +2Multi-Agent DebateMulti-Agent Reasoning

    Applied Artificial Intelligence Initiative Deakin University, Australia

  14. From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts

    Mar 12, 2026Sunil PrakashMulti-Agent DeliberationMulti-Agent Reasoning

    Indian School of Business, India

  15. Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy

    Mar 6, 2026Yuhan Liu, Juntian Zhang, Yichen Wu +4Multi-Agent DebateMulti-Agent Consensus

    Mohamed bin Zayed University of Artificial Intelligence · Gaoling School of Artificial Intelligence, Renmin University of China · Harvard University

  16. Knowledge Divergence and the Value of Debate for Scalable Oversight

    Mar 5, 2026Robin YoungMulti-Agent DebateScalable Oversight

    Department of Computer Science and Technology, University of Cambridge, Cambridge, UK

  17. Multi-Agent Debate with Memory Masking

    Mar 3, 2026Hongduan Tian, Xiao Feng, Ziyuan Zhao +3Multi-Agent DebateLLM Reasoning

    TMLR Group, Hong Kong Baptist University · Search Algorithm Group, WeChat, Tencent

  18. Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning

    Mar 1, 2026Dan Qiao, Binbin Chen, Fengyu Cai +7Multi-Agent DebateEpistemic Uncertainty

    School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · ByteDance, Beijing, China · Technical University of Darmstadt, Darmstadt, Germany +2

  19. MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis

    Mar 1, 2026Yuqi Zhan, Xinyue Wu, Tianyu Lin +6Multi-Agent LLM SystemsMedical Report Generation

    Hangzhou Dianzi University · Zhejiang University · Children’s Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescents’ Health and Diseases

  20. RUMAD: Reinforcement-Unifying Multi-Agent Debate

    Feb 27, 2026Chao Wang, Han Lin, Huaze Tang +2Communication Topology OptimizationMulti-Agent Debate

    Tsinghua University, Shenzhen, China · Zhejiang University, Hangzhou, China

  21. CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety

    Feb 26, 2026Umid Suleymanov, Rufiz Bayramov, Suad Gafarli +4Zero-Shot Policy TransferLanguage Model Safety Evaluation

    Department of Computer Science, Virginia Tech · School of IT and Engineering, ADA University · School of Law, ADA University

  22. Debate2Create: Robot Co-design via Multi-Agent LLM Debate

    Oct 29, 2025Kevin Qiu, Marek CyganRobot Morphology-Control Co-DesignMulti-Agent Debate

    University of Warsaw · 2IDEAS NCBR · 3Nomagic

  23. When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

    Oct 23, 2025Yongqiang Chen, Gang Niu, James Cheng +2Multi-Agent DebateMulti-Agent Collaboration

    1The Chinese University of Hong Kong · 2RIKEN Center for Advanced Intelligence Project · 3Hong Kong Baptist University +1

  24. Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate

    Oct 11, 2025Pratik S. Sachdeva, Tom van NuenenLLM Decision-MakingMoral Reasoning in Language Models

    D-Lab, University of California, Berkeley