👋 This is the project page for our paper: “BOOKWORLD: From Novels to Interactive Agent Societies for Story Creation” .
Check out further information below.
Everything you need to know about our work.
We are working on an online interactive demo.
Code for running customized simulation.
Recent advances in large language models (LLMs) have enabled social simulation through multi-agent systems.
Prior efforts focus on agent societies created from scratch, assigning agents with newly defined personas.
However, simulating established fictional worlds and characters remain largely underexplored, despite its significant practical value.
In this paper, we introduce BookWorld, a comprehensive system for constructing and simulating book-based multi-agent societies.
BookWorld’s design covers comprehensive real-world intricacies, including diverse and dynamic characters, fictional worldviews, geographical constraints and changes, e.t.c.
BookWorld enables diverse applications including story generation, interactive games and social simulation, offering novel ways to extend and explore beloved fictional works. Through extensive experiments, we demonstrate that BookWorld generates creative, high-quality stories while maintaining fidelity to the source books, surpassing previous methods with a win rate of 75.36%.
Recent advances in LLMs have enabled social simulation through multi-agent systems. Prior efforts focus on agent societies created from scratch, assigning agents with newly defined personas. However, simulating established fictional worlds and characters remain largely underexplored, despite its significant practical value. In our paper titled “BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation”, we introduce BookWorld, a comprehensive system for constructing and simulating book-based multi-agent societies.
BookWorld provides a complete pipeline from data collection to social simulation, and finally, rephrasing into novelistic text.
Before the simulation starts, we extract character and worldview data from source materials, used for book-to-system construction.
The simulation begins by initializing role agents and the world agent, loading character profiles, the geospatial map, the worldview data and other necessary information.
After the simulation ends, we collect the simulation records and apply LLMs to rephrase the records into the final, novel-style story.
If you find this work useful to your research, please kindly cite our paper:
@misc{ran2025bookworldnovelsinteractiveagent,
title={BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation},
author={Yiting Ran and Xintao Wang and Tian Qiu and Jiaqing Liang and Yanghua Xiao and Deqing Yang},
year={2025},
eprint={2504.14538},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2504.14538},
}