mlsanityData to 7 Oct 2026

Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation

arXiv 2406.19643 ↗First posted 28 Jun 2024cs.CL cs.AIcited by 29

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

Abstract (arXiv)

Writing persuasive arguments is a challenging task for both humans and machines. It entails incorporating high-level beliefs from various perspectives on the topic, along with deliberate reasoning and planning to construct a coherent narrative. Current language models often generate surface tokens autoregressively, lacking explicit integration of these underlying controls, resulting in limited output diversity and coherence. In this work, we propose a persona-based multi-agent framework for argument writing. Inspired by the human debate, we first assign each agent a persona representing its high-level beliefs from a unique perspective, and then design an agent interaction process so that the agents can collaboratively debate and discuss the idea to form an overall plan for argument writing. Such debate process enables fluid and nonlinear development of ideas. We evaluate our framework on argumentative essay writing. The results show that our framework can generate more diverse and persuasive arguments through both automatic and human evaluations.

Key facts. Cited by 29 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 26 of its 42 references that are in the map. First posted on arXiv 28 Jun 2024.

Builds on

26 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction31 Oct
  2. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 24

  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. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  7. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  8. 2020Evaluation of Text Generation: A Surveycited by 275
  9. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 246
  10. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  11. 2023Does Writing with Language Models Reduce Content Diversity?cited by 190
  12. 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 140
12 more
  1. 2023PRD: Peer Rank and Discussion Improve Large Language Model based Evaluationscited by 114
  2. 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
  3. 2020Content Planning for Neural Story Generation with Aristotelian Rescoringcited by 92
  4. 2023RecurrentGPT: Interactive Generation of (Arbitrarily) Long Textcited by 84
  5. 2024Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debatecited by 48
  6. 2019Argument Generation with Retrieval, Planning, and Realizationcited by 45
  7. 2018Neural Argument Generation Augmented with Externally Retrieved Evidencecited by 34
  8. 2022PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generationcited by 30
  9. 2024CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Modelscited by 26
  10. 2023Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinkingcited by 19
  11. 2021Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Rewardcited by 5
  12. 2022MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspectivecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 16.

29 papers.

Sort:

By area:

  1. 2025LLM Agents for Education: Advances and Applicationscited by 59
  2. 2025The Homogenizing Effect of Large Language Models on Human Expression and Thoughtcited by 35
  3. 2025Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamicscited by 19
  4. 2025A Cognitive Writing Perspective for Constrained Long-Form Text Generationcited by 14
  5. 2025ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mindcited by 12
  6. 2025CortexDebate: Debating Sparsely and Equally for Multi-Agent Debatecited by 6
  7. 2025Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agentscited by 5
  8. 2025A Review of Incorporating Psychological Theories in LLMscited by 5
  9. 2025DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agentscited by 5
  10. 2026DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttalcited by 4
  11. 2026Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verificationcited by 4
  12. 2026EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibriumcited by 3
17 more
  1. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challengescited by 3
  2. 2025Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agentscited by 2
  3. 2025The High Cost of Incivility: Quantifying Interaction Inefficiency via Multi-Agent Monte Carlo Simulationscited by 1
  4. 2026DALDALL: Data Augmentation for Lexical and Semantic Diverse in Legal Domain by leveraging LLM-Personacited by 1
  5. 2026Structuring the Space of Perspectivescited by 1
  6. 2025From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discoursecited by 0
  7. 2025CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Modelscited by 0
  8. 2026MIND: Multi-agent inference for negotiation dialogue in travel planningcited by 0
  9. 2026Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulationscited by 0
  10. 2026LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observabilitycited by 0
  11. 2026A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarizationcited by 0
  12. 2026More Is Not More: What Matters for Diversity in LLM Opinions?cited by 0
  13. 2026Towards High-Level Semantic Intelligencecited by 0
  14. 2026ARGUS: Theory-of-Mind Guided Argument Generation with Strategy-Aware Planning and Knowledge Groundingcited by 0
  15. 2026Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity?cited by 0
  16. 2026PTCG: Persona-guided Tree-based Counterargument Generationcited by 0
  17. 2026DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models
  2. 2024Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate
  3. 2024Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
  4. 2026Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
  5. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  6. 2026The Virtual Roundtable: Multi-Agent Personas Simulating the Dynamics of Human Brainstorming
  7. 2025Enhancing Multi-Agent Debate System Performance via Confidence Expression
  8. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?