mlsanityData to 14 Oct 2026

GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion

arXiv 2409.14051 ↗First posted 21 Sep 2024cs.CL cs.AIcited by 67

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with Self-Consistency, Tree-Of-Thoughts, and multi-agent debates. In the context of multi-agent debates, significant performance improvements can be achieved with an increasing number of agents and debate rounds. However, the escalation in the number of agents and debate rounds can drastically raise the tokens cost of debates, thereby limiting the scalability of the multi-agent debate technique. To better harness the advantages of multi-agent debates in logical reasoning tasks, this paper proposes a method to significantly reduce token cost in multi-agent debates. This approach involves dividing all agents into multiple debate groups, with agents engaging in debates within their respective groups and sharing interim debate results between groups. Comparative experiments across multiple datasets have demonstrated that this method can reduce the total tokens by up to 51.7% during debates and while potentially enhancing accuracy by as much as 25%. Our method significantly enhances the performance and efficiency of interactions in the multi-agent debate.

Key facts. Cited by 67 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 35 of its 45 references that are in the map. First posted on arXiv 21 Sep 2024.

Builds on

35 of 45 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Improving Multi-Agent Debate with Sparse Communication Topology17 Jun
  2. 2023Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration14 Nov
  3. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration30 Sep
  4. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  7. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  8. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  10. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  11. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  12. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
19 more
  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  2. 2023Let's Verify Step by Stepcited by 3,789
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  9. 2023PaLM 2 Technical Reportcited by 1,162
  10. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  11. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  12. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  13. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  14. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  15. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 207
  16. 2023Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4cited by 202
  17. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  18. 2023Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debatecited by 97
  19. 2023Tab-CoT: Zero-shot Tabular Chain of Thoughtcited by 42

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 33; 2026: 34.

67 papers.

Sort:

By area:

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  2. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  3. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?cited by 81
  4. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 56
  5. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  6. 2025Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoningcited by 29
  7. 2025MAS-ZERO: Designing Multi-Agent Systems with Zero Supervisioncited by 28
  8. 2025From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibriumcited by 26
  9. 2025S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiencycited by 22
  10. 2025When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoningcited by 21
  11. 2025Enhancing Multi-Agent Debate System Performance via Confidence Expressioncited by 19
  12. 2025Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learningcited by 18
38 more
  1. 2026Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judgecited by 18
  2. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 16
  3. 2025Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systemscited by 15
  4. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  5. 2025How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMscited by 12
  6. 2025The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systemscited by 11
  7. 2025Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judgecited by 11
  8. 2025Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debatecited by 10
  9. 2025iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inferencecited by 10
  10. 2026Multi-Agent Debate with Memory Maskingcited by 10
  11. 2026Token-Level LLM Collaboration via FusionRoutecited by 9
  12. 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learningcited by 9
  13. 2025Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Studycited by 8
  14. 2025HoarePrompt: Structural Reasoning About Program Correctness in Natural Languagecited by 7
  15. 2025CortexDebate: Debating Sparsely and Equally for Multi-Agent Debatecited by 7
  16. 2026Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoningcited by 5
  17. 2026Self-Improvement of Large Language Models: A Technical Overview and Future Outlookcited by 5
  18. 2025CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Modelscited by 4
  19. 2026Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retentioncited by 4
  20. 2026Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verificationcited by 4
  21. 2025Debate over Mixed-knowledge: A Robust Multi-Agent Reasoning Framework for Incomplete Knowledge Graph Question Answeringcited by 3
  22. 2025Latent Debate: A Surrogate Framework for Interpreting LLM Thinkingcited by 3
  23. 2025Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcarecited by 3
  24. 2025The Effect of Belief Boxes and Open-mindedness on Persuasioncited by 3
  25. 2026RUMAD: Reinforcement-Unifying Multi-Agent Debatecited by 3
  26. 2026Multi-Agent Dialectical Refinement for Enhanced Argument Classificationcited by 3
  27. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challengescited by 3
  28. 2025PD3: A Project Duplication Detection Framework via Adapted Multi-Agent Debatecited by 2
  29. 2025AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Datacited by 2
  30. 2025Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Taskscited by 2
  31. 2026EMS: Multi-Agent Voting via Efficient Majority-then-Stoppingcited by 2
  32. 2026HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debatecited by 2
  33. 2026Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scalingcited by 2
  34. 2026Multi-Agent LLMs Fail to Explore Each Othercited by 2
  35. 2025Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoningcited by 1
  36. 2026M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalitiescited by 1
  37. 2026Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debatecited by 1
  38. 2026Traceable Latent Variable Discovery Based on Multi-Agent Collaborationcited by 1

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
  2. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  3. 2024Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks
  4. 2025Free-MAD: Consensus-Free Multi-Agent Debate
  5. 2024Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate
  6. 2026Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
  7. 2026Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
  8. 2026Demystifying Multi-Agent Debate: The Role of Confidence and Diversity