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

TL;DR

This paper introduces a persona-driven multi-agent framework inspired by human debate, enabling diverse and persuasive argument generation by simulating collaborative discussion among agents with distinct perspectives.

Contribution

It presents a novel multi-agent debate framework that incorporates high-level beliefs for improved diversity and coherence in argument writing, addressing limitations of current language models.

Findings

Generated arguments are more diverse and persuasive.

Framework outperforms baselines in automatic and human evaluations.

Enables nonlinear development of ideas through debate process.

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.