用多个专业角色协作写故事，让AI生成更像真人写的长篇叙事。
Agents' Room: Narrative Generation through Multi-step Collaboration
- 拆解写作任务，由不同角色分工完成剧情、人物、语言等环节。
- 在专家评测中，生成故事受欢迎度高于基线系统。
- 适合对复杂叙事生成感兴趣的研究者和创作者。
创作引人入胜的虚构故事涉及情节构建、角色塑造和生动语言等多个方面。尽管大语言模型在故事生成上展现出潜力，但当前仍严重依赖复杂的提示工程，限制了实际应用。本文提出 Agents' Room，一个受叙事理论启发的生成框架，将叙事写作分解为由专业化智能体协同完成的子任务。为验证该方法，我们构建了高质数据集 Tell Me A Story，包含复杂写作提示与人类撰写的完整故事，并设计了专用于评估长篇叙事的新型评估体系。实验表明，通过协作与分工，Agents' Room 生成的故事在专家评价中优于基线系统。我们还通过自动化与人工评估指标进行了全面分析。
原文摘要 · Abstract (English)
Writing compelling fiction is a multifaceted process combining elements such as crafting a plot, developing interesting characters, and using evocative language. While large language models (LLMs) show promise for story writing, they currently rely heavily on intricate prompting, which limits their use. We propose Agents' Room, a generation framework inspired by narrative theory, that decomposes narrative writing into subtasks tackled by specialized agents. To illustrate our method, we introduce Tell Me A Story, a high-quality dataset of complex writing prompts and human-written stories, and a novel evaluation framework designed specifically for assessing long narratives. We show that Agents' Room generates stories that are preferred by expert evaluators over those produced by baseline systems by leveraging collaboration and specialization to decompose the complex story writing task into tractable components. We provide extensive analysis with automated and human-based metrics of the generated output.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。