mlsanityData to 7 Oct 2026

Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate

arXiv 2408.04472 ↗First posted 8 Aug 2024cs.CLcited by 16

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Competitive debate is a complex task of computational argumentation. Large Language Models (LLMs) suffer from hallucinations and lack competitiveness in this field. To address these challenges, we introduce Agent for Debate (Agent4Debate), a dynamic multi-agent framework based on LLMs designed to enhance their capabilities in competitive debate. Drawing inspiration from human behavior in debate preparation and execution, Agent4Debate employs a collaborative architecture where four specialized agents, involving Searcher, Analyzer, Writer, and Reviewer, dynamically interact and cooperate. These agents work throughout the debate process, covering multiple stages from initial research and argument formulation to rebuttal and summary. To comprehensively evaluate framework performance, we construct the Competitive Debate Arena, comprising 66 carefully selected Chinese debate motions. We recruit ten experienced human debaters and collect records of 200 debates involving Agent4Debate, baseline models, and humans. The evaluation employs the Debatrix automatic scoring system and professional human reviewers based on the established Debatrix-Elo and Human-Elo ranking. Experimental results indicate that the state-of-the-art Agent4Debate exhibits capabilities comparable to those of humans. Furthermore, ablation studies demonstrate the effectiveness of each component in the agent structure.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 24 of its 44 references that are in the map. First posted on arXiv 8 Aug 2024.

Builds on

24 of 44 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2020Scaling Laws for Neural Language Modelscited by 6,411
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  10. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  11. 2024Qwen2 Technical Reportcited by 2,076
  12. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
11 more
  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  3. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  4. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  5. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 154
  6. 2023CharacterChat: Learning towards Conversational AI with Personalized Social Supportcited by 58
  7. 2019Argument Generation with Retrieval, Planning, and Realizationcited by 45
  8. 2023Exploring the Potential of Large Language Models in Computational Argumentationcited by 42
  9. 2017Neural End-to-End Learning for Computational Argumentation Miningcited by 41
  10. 2024Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLMcited by 21
  11. 2024SocraSynth: Multi-LLM Reasoning with Conditional Statisticscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 5.

16 papers.

Sort:

By area:

  1. 2024SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinementcited by 124
  2. 2025Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Modelscited by 12
  3. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 12
  4. 2025Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Surveycited by 10
  5. 2025iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inferencecited by 10
  6. 2024Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generationcited by 5
  7. 2025CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressurescited by 5
  8. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 5
  9. 2025InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debatingcited by 4
  10. 2025R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memorycited by 4
  11. 2025Strategic Planning and Rationalizing on Trees Make LLMs Better Debaterscited by 2
  12. 2025BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Actscited by 2
4 more
  1. 2025Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulationcited by 1
  2. 2026Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studiescited by 1
  3. 2026Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentationcited by 0
  4. 2026PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
  2. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  3. 2024GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion
  4. 2026Demystifying Multi-Agent Debate: The Role of Confidence and Diversity
  5. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
  6. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
  7. 2026Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
  8. 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detection