Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation
🤖 AI Summary
Current automated writing models exhibit significant limitations in generating argumentative essays characterized by depth, logical coherence, and multi-perspective critical reasoning—particularly in integrating opposing viewpoints while preserving narrative consistency. To address this, we propose a persona-driven multi-agent debate framework wherein agents explicitly model role-based beliefs and collaboratively construct argument structures through dynamic, non-linear interactive debate, thereby overcoming bottlenecks of conventional autoregressive models in viewpoint integration and inferential coherence. Our approach integrates multi-agent systems, structured reasoning chains, LLM-powered agent coordination protocols, and fine-grained prompt engineering. Experiments on argumentative essay generation demonstrate a 32% increase in argument diversity, a +2.1/5 improvement in human-assessed persuasiveness (on a 5-point scale), and state-of-the-art performance on BERTScore and Distinct-n metrics.
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Automatic Writing
Coherent Generation
Argumentative Content
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-perspective Debate Simulation
Enhanced Logical Coherence
Persuasive Writing Improvement
🔎 Similar Papers
No similar papers found.
