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

154 papers16 papers in the last four weeks, down 11% on the four weeks before. 0.1% of all new papers.

  1. Towards a Theory of Learnability via Debate

    Nov 12, 2026Tosca Lechner, Vinayak Pathak, Sivan Sabato +1Multi-Agent Debate

  2. Debate to Deceive: Poisoning LLM's Fact-Checking via Game-Theoretic Multi-Agent Debate

    Nov 5, 2026Liting Huang, Huizhi Liang, Yi Lei +2Adversarial Attacks on LLMsDeception in Language Models

  3. Beyond Risk Cues: A Mechanism-Level Benchmark and Verifiable Debate for Scam Video Detection on the Web

    Nov 4, 2026Yifan Wang, Junyu Lu, Shun Zhang +6Video Content ModerationMulti-Agent Debate

  4. When Debate Amplifies Risk: Social-Bias Vulnerabilities in Multi-Agent Safety Deliberation

    Nov 3, 2026Qinghua Mao, Xi Lin, Yuxin Qi +3LLM Agent SafetyMulti-Agent Debate

  5. HEDGE: Gated Hypergraph Memory for Scalable Multi-Agent Debate

    Oct 28, 2026Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zirui ZhouMemory Management for LLM AgentsMulti-Agent Debate

  6. Replication or Corroboration? An Axiomatic Framework for Evidential Dependence in Multi-Agent Debate

    Oct 26, 2026Hoang-Loc Cao, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen +6Bipolar Argumentation FrameworksMulti-Agent Debate

  7. Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement

    Oct 21, 2026Kardelen Subasi, Jarosław A. ChudziakLLM AuditingLLM Hallucination Mitigation

  8. Value-Rich, Differently Organized: Measuring Value Expression and Organization in AI-Generated Debates

    Oct 20, 2026Maoyuan Li, Haoyuan Li, Zhongsheng Wang +1Language Model Generation EvaluationMulti-Agent Debate

  9. Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not

    Oct 20, 2026Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto +14Multi-Agent DebateHuman Oversight of AI

  10. Think More or Read More? A Token-Budget Theory of Reasoning with Shared Context

    Oct 16, 2026Manh Nguyen, Sunil Gupta, Hung LeEfficient Language Model ReasoningMulti-Agent Debate

  11. Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions

    Oct 15, 2026Liangjie Huang, Henry Peng Zou, Wei-Chieh Huang +3Multi-Agent LLM SystemsLLM Agent Reliability

  12. Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

    Oct 13, 2026Yuan Liu, Haoyue Peng, Fanliang Hu +2Multi-Agent DeliberationMulti-Agent Debate

  13. Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate

    Oct 12, 2026Seungdong Yoa, Ye Seul Sim, Suhee Yoon +5Multi-Agent DebateMulti-Agent Reasoning

  14. From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage

    Oct 7, 2026Saimon Amanuel Tsegai, Alex Kantchelian, Danfeng +2LLM Agent SecurityAI Agent Reliability

  15. DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate

    Oct 4, 2026Khanh-Binh Nguyen, Van Dai Do, Tien Anh Nguyen +2Multi-Agent DebateMultimodal Reasoning

  16. When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning

    Oct 3, 2026Zihao Zhao, Tunyu Zhang, Haizhou Shi +3Multi-Agent DebateMulti-Agent Reasoning

  17. MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate

    Sep 30, 2026Jiaming Zhang, Yuwan Liu, Yue Huang +1Multi-Agent DebateAI Agent Security

  18. MADBench: Benchmarking the Security of Multi-Agent Debate

    Sep 30, 2026Yuwan Liu, Jiaming Zhang, Yue Huang +1Adversarial Attacks on LLMsMulti-Agent Debate

  19. When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate

    Sep 30, 2026Duofeng Xu, Bryan Hooi, Dandan QiaoMulti-Agent Debate

  20. Multi-agent discussion gains less when dissent is withheld

    Sep 29, 2026Chand Sahil Mansuri, Xin Wang, Mengying Li +4Multi-Agent LLM SystemsOpinion Dynamics

  21. Measuring Collapse and Correction in Homogeneous-Panel LLM Debate

    Sep 28, 2026Xin Li, Mengbing Liu, Chau YuenLLM EvaluationLLM Auditing

  22. Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning

    Sep 27, 2026Ruosong Ye, Caiqi Zhang, Jiahao Li +9Test-Time ScalingMulti-Agent Debate

  23. Beyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models

    Sep 26, 2026Leonardo Ferreira, Gardenia Liu, Kaden ZhengMulti-Agent DebateMulti-Agent Systems