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

arXiv: https://arxiv.org/abs/2408.04472 · HTML: https://mlsanity.com/paper/2408.04472/

## Key facts

- Cited by 16 papers in the map (data through 14 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.

## Placed in

- 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, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [Argument Generation with Retrieval, Planning, and Realization](https://mlsanity.com/paper/1906.03717/) (2019)
- [Exploring the Potential of Large Language Models in Computational Argumentation](https://mlsanity.com/paper/2311.09022/) (2023)
- [Neural End-to-End Learning for Computational Argumentation Mining](https://mlsanity.com/paper/1704.06104/) (2017)
- [Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM](https://mlsanity.com/paper/2403.08010/) (2024)
- [SocraSynth: Multi-LLM Reasoning with Conditional Statistics](https://mlsanity.com/paper/2402.06634/) (2024)

## Built on by (most cited first, 16 of 16)

- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [LatentMem: Customizing Latent Memory for Multi-Agent Systems](https://mlsanity.com/paper/2602.03036/) (2026)
- [Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models](https://mlsanity.com/paper/2505.18596/) (2025)
- [Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey](https://mlsanity.com/paper/2504.14520/) (2025)
- [iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference](https://mlsanity.com/paper/2511.11306/) (2025)
- [Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation](https://mlsanity.com/paper/2412.05342/) (2024)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures](https://mlsanity.com/paper/2508.11915/) (2025)
- [InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating](https://mlsanity.com/paper/2506.18102/) (2025)
- [R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory](https://mlsanity.com/paper/2512.24684/) (2025)
- [Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters](https://mlsanity.com/paper/2505.14886/) (2025)
- [BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts](https://mlsanity.com/paper/2512.24885/) (2025)
- [Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation](https://mlsanity.com/paper/2510.13884/) (2025)
- [Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies](https://mlsanity.com/paper/2604.15607/) (2026)
- [Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation](https://mlsanity.com/paper/2606.01020/) (2026)
- [PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluation](https://mlsanity.com/paper/2608.16276/) (2026)

## 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.