BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation
원문 초록
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%. The code of this paper can be found at the project page: https://bookworld2025.github.io/.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
StoryWriter: A Multi-Agent Framework for Long Story Generation
Consistent Story Generation with Asymmetry Zigzag Sampling
Counterfactual reasoning: an analysis of in-context emergence
StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation
Learning to Reason for Long-Form Story Generation
Whose story is it? Personalizing story generation by inferring author styles
토론
이 논문과 연결된 포럼 글이 아직 없습니다.