BOOKWORLD: From Novels to Interactive Agent Societies for Story Creation
Yiting Ran, Xintao Wang, Tian Qiu, Jiaqing Liang, Yanghua Xiao, Deqing Yang
Abstract
Recent advances in large language models (LLMs) have enabled social simulation through multiagent 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%. The code of this paper can be found at the project page: https://bookworld2025.github.io/ Castle Village Forest Cave Castle Here we are-the heart of the empire. I hope y&# This tapestry... it's new. The threads are fresh, R# Forest (kneeling to examine a blackened timber) "The burr# (kneeling to examine a blackened timber) "The bu# Village (kneeling to examine a blackened timber) "The bu# Figure 1: A preview of BookWorld. Characters in the same location can interact with each other based on their goals and other factors. The map is represented as a discrete graph, where characters can traverse between adjacent locations spending several turns.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 9c1098ee-1308-414e-a1f9-ce2b33b0fca1Cited by top-tier papers3
- Deriving Character Logic from Storyline as Codified Decision TreesLetian Peng, Kun Zhou, Longfei Yun, Yupeng Hou et al.ACL 2026 · 3 citations
- Codified Finite-state Machines for Role-playingLetian Peng, Yupeng Hou, Kun Zhou, Jingbo ShangICLR 2026 · 1 citation
- EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative EvolutionShiyu He, Minchi Kuang, Mengxian Wang, Bin Hu et al.ACL 2026
Builds on7
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent DebateChi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu et al.ICLR 2024 · 871 citations
- SOTOPIA: Interactive Evaluation for Social Intelligence in Language AgentsXuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang et al.ICLR 2024 · 288 citations
- Co-Writing Screenplays and Theatre Scripts with Language Models: Evaluation by Industry ProfessionalsPiotr Mirowski, Kory W. Mathewson, Jaylen Pittman, Richard EvansCHI 2023 · 235 citations
- Content Planning for Neural Story Generation with Aristotelian RescoringSeraphina Goldfarb-Tarrant, Tuhin Chakrabarty, Ralph M. Weischedel, Nanyun PengEMNLP 2020 · 106 citations
Related papers
- SimWorld: An Open-ended Simulator for Agents in Physical and Social WorldsXiaokang Ye, Jiawei Ren, Yan Zhuang, Xuhong He et al.NeurIPS 2025 · 8 citations
- Human Simulacra: Benchmarking the Personification of Large Language ModelsQiujie Xie, Qiming Feng, Tianqi Zhang, Qingqiu Li et al.ICLR 2025
- SimSpark: Interactive Simulation of Social Media BehaviorsZiyue Lin, Yi Shan, Lin Gao, Xinghua Jia et al.CSCW 2025 · 5 citations
- Cinema Multiverse Lounge: Enhancing Film Appreciation via Multi-Agent ConversationsJeongwoo Ryu, Kyusik Kim, Dongseok Heo, Hyungwoo Song et al.CHI 2025 · 9 citations
- Patchview: LLM-powered Worldbuilding with Generative Dust and Magnet VisualizationJohn Joon Young Chung, Max KreminskiUIST 2024 · 29 citations
