Multi-Agent Based Character Simulation for Story Writing
Yu Tian, Ken Shi, Zixin Zhao, Gerald M. Penn · 2025
This work proposes a novel multi-agent storygeneration system that writes stories from a narrative plan.Traditional approaches tend to generate a section of text directly from its outline.Our system, by contrast, divides this elaboration process into role-play and rewrite steps, where the former step enacts the story in chronological order with LLM-backed character agents, and the latter step refines the roleplay result to align with a narrative plan.We show that the stories produced by our system are preferable to two other LLM-based storygeneration approaches.We attribute this advancement to the benefits of incorporating a character-based simulation strategy.