Long story generation remains a challenge for existing large language models (LLMs), primarily due to two main factors: (1) discourse coherence, which requires plot consistency, logical coherence, and completeness in the long-form generation, and (2) narrative complexity, which requires an interwoven and engaging narrative. To address these challenges, we propose StoryWriter, a multi-agent story generation framework, which consists of three main modules: (1) outline agent, which generates event-based outlines containing rich event plots, character, and event-event relationships. (2) planning agent, which further details events and plans which events should be written in each chapter to maintain an interwoven and engaging story. (3) writing agent, which dynamically compresses the story history based on the current event to generate and reflect new plots, ensuring the coherence of the generated story. We conduct both human and automated evaluation, and StoryWriter significantly outperforms existing story generation baselines in both story quality and length. Furthermore, we use StoryWriter to generate a dataset, which contains about high-quality long stories, with an average length of words. We train the model Llama3.1-8B and GLM4-9B using supervised fine-tuning on LongStory and develop StoryWriter_GLM and StoryWriter_GLM, which demonstrates advanced performance in long story generation.
View on arXiv@article{xia2025_2506.16445,
title={ StoryWriter: A Multi-Agent Framework for Long Story Generation },
author={ Haotian Xia and Hao Peng and Yunjia Qi and Xiaozhi Wang and Bin Xu and Lei Hou and Juanzi Li },
journal={arXiv preprint arXiv:2506.16445},
year={ 2025 }
}