[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-yingpengma--Awesome-Story-Generation":3,"tool-yingpengma--Awesome-Story-Generation":64},[4,17,25,39,48,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,14,15],"开发框架","Agent","语言模型","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":10,"last_commit_at":23,"category_tags":24,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,15],{"id":26,"name":27,"github_repo":28,"description_zh":29,"stars":30,"difficulty_score":10,"last_commit_at":31,"category_tags":32,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[33,34,35,36,14,37,15,13,38],"图像","数据工具","视频","插件","其他","音频",{"id":40,"name":41,"github_repo":42,"description_zh":43,"stars":44,"difficulty_score":45,"last_commit_at":46,"category_tags":47,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,3,"2026-04-04T04:44:48",[14,33,13,15,37],{"id":49,"name":50,"github_repo":51,"description_zh":52,"stars":53,"difficulty_score":45,"last_commit_at":54,"category_tags":55,"status":16},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",74913,"2026-04-05T10:44:17",[15,33,13,37],{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":45,"last_commit_at":62,"category_tags":63,"status":16},2181,"OpenHands","OpenHands\u002FOpenHands","OpenHands 是一个专注于 AI 驱动开发的开源平台，旨在让智能体（Agent）像人类开发者一样理解、编写和调试代码。它解决了传统编程中重复性劳动多、环境配置复杂以及人机协作效率低等痛点，通过自动化流程显著提升开发速度。\n\n无论是希望提升编码效率的软件工程师、探索智能体技术的研究人员，还是需要快速原型验证的技术团队，都能从中受益。OpenHands 提供了灵活多样的使用方式：既可以通过命令行（CLI）或本地图形界面在个人电脑上轻松上手，体验类似 Devin 的流畅交互；也能利用其强大的 Python SDK 自定义智能体逻辑，甚至在云端大规模部署上千个智能体并行工作。\n\n其核心技术亮点在于模块化的软件智能体 SDK，这不仅构成了平台的引擎，还支持高度可组合的开发模式。此外，OpenHands 在 SWE-bench 基准测试中取得了 77.6% 的优异成绩，证明了其解决真实世界软件工程问题的能力。平台还具备完善的企业级功能，支持与 Slack、Jira 等工具集成，并提供细粒度的权限管理，适合从个人开发者到大型企业的各类用户场景。",70612,"2026-04-05T11:12:22",[15,14,13,36],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":82,"owner_website":83,"owner_url":84,"languages":85,"stars":90,"forks":91,"last_commit_at":92,"license":81,"difficulty_score":93,"env_os":94,"env_gpu":95,"env_ram":95,"env_deps":96,"category_tags":99,"github_topics":100,"view_count":111,"oss_zip_url":81,"oss_zip_packed_at":81,"status":16,"created_at":112,"updated_at":113,"faqs":114,"releases":115},2048,"yingpengma\u002FAwesome-Story-Generation","Awesome-Story-Generation","This repository collects an extensive list of awesome papers about Story Generation \u002F Storytelling, exclusively focusing on the era of Large Language Models (LLMs).","Awesome-Story-Generation 是一个专注于大语言模型（LLM）时代的开源项目，旨在系统性地收集并整理关于故事生成与叙事创作的顶尖学术论文。在大模型引发技术范式转移的背景下，它解决了研究人员和开发者难以从海量文献中快速定位最新、最相关研究成果的痛点，提供了一份按时间排序且持续更新的权威指南。\n\n该项目特别适合人工智能领域的研究人员、算法工程师以及对自动化创作感兴趣的技术爱好者使用。其核心亮点在于精细化的分类体系，将复杂的研究方向梳理为“规划与写作”、“多智能体协作”、“多模态融合”、“可控性优化”及“个性化创作”等关键板块。无论是想探索如何让 AI 写出逻辑更严密的长篇小说，还是研究如何评估故事质量，用户都能在此找到对应的前沿论文、代码资源及数据集。通过汇聚全球智慧，Awesome-Story-Generation 成为了连接理论创新与技术实践的桥梁，助力社区共同推动智能叙事技术的发展。","\u003Ch1 align=\"center\">Awesome-Story-Generation\u003C\u002Fh1>\n\n\u003Cdiv align=\"center\">Contributed by \u003Ca href=\"https:\u002F\u002Fyingpengma.github.io\u002F\">Yingpeng Ma\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fmantle2048.github.io\u002F\">Yan Ma\u003C\u002Fa>\u003C\u002Fdiv>\n\n##\n\n🔥 Recognizing the paradigm shift brought by **Large Language Models**, we now focus exclusively on LLM-related research.\n\nFor those interested in previous research before LLM era, an archived version is available in [Old Version](old_version.md) (this archive is **no longer maintained**). \n\n## Table of Contents\n\n- [Introduction](#introduction)\n\u003C!--\n- [Related Repository](#related-repository)\n-->\n- [Papers](#papers)\n  - [Overview](#overview)\n  - [Plan And Write](#plan-and-write)\n  - [Multi Agent](#multi-agent)\n  - [Multimodality](#multimodality)\n  - [Better Storytelling](#better-storytelling)\n  - [More Controllable](#more-controllable)\n  - [More Personalized](#more-personalized)\n  - [Evaluation](#evaluation)\n  - [Dataset](#dataset)\n- [Public Resources](#public-resources)\n\n## Introduction\n\nThis repository collects awesome papers about **Story Generation \u002F Storytelling** in LLM era.\n\nPapers are listed chronologically (most recent first).\n\n**Thank you for the stars!** We're continuously updating with the latest research. Cheers! 🍻\n\nYour contributions matter! Please help keep this list current and accurate by opening issues or PRs for any mistakes or missing papers.\n\nContact: `mayingpeng33 [AT] gmail [DOT] com`\n\n\u003C!--\n## Related Repository\n|**[Awesome-LLM-Characters](https:\u002F\u002Fgithub.com\u002Fyingpengma\u002FAwesome-LLM-Characters)**|\n|:---:|\n-->\n\n## Papers\nEg. `ACL-20XX` **Title** [paper] [code] .. [authors]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-count-blue)]()\n\n### Overview\n- `ArXiv-2024` **What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.14622) [Dingyi Yang, Qin Jin] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `CHI-2024` **The Value, Benefits, and Concerns of Generative AI-Powered Assistance in Writing** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.12004) [Zhuoyan Li, Chen Liang, Jing Peng, Ming Yin] [Mainly about ChatGPT, not including other models] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-59-blue)]() \n- `ArXiv-2024` **Weaver: Foundation Models for Creative Writing** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.17268) [Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, ... , Yuchen Eleanor Jiang, Wangchunshu Zhou] [Foundation Models which focus on writing capabilities] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-20-blue)]()\n- `Neurocomputing-2023` **Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.04634) [Yuxin Wang, Jieru Lin, Zhiwei Yu, Wei Hu, Börje F. Karlsson] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-39-blue)]()\n- `EMNLP Findings-2023` **Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.18783) [Lixing Zhu, Runcong Zhao, Lin Gui, Yulan He] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]()\n\n### Plan And Write\n- `ArXiv-2025` **Learning to Reason for Long-Form Story Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.22828v2) [Alexander Gurung, Mirella Lapata] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `NAACL-2025` **Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.13575) [Qianyue Wang, Jinwu Hu, Zhengping Li, Yufeng Wang, daiyuan li, Yu Hu, Mingkui Tan] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `EMNLP-2024` **Collective Critics for Creative Story Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.02428) [Minwook Bae, Hyounghun Kim] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `ACL-2024` **Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.08506) [Lei Huang, Jiaming Guo, Guanhua He, Xishan Zhang, Rui Zhang, Shaohui Peng, Shaoli Liu, Tianshi Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-2-blue)]()\n- `ACL Workshop-2025` **Guiding and Diversifying LLM-Based Story Generation via Answer Set Programming** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.00554) [Phoebe J. Wang, Max Kreminski] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `NAACL-2025` **Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.13919) [Yukyung Lee, Soonwon Ka, Bokyung Son, Pilsung Kang, Jaewook Kang]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `EACL-2024` **Creating Suspenseful Stories: Iterative Planning with Large Language Models** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.17119) [Kaige Xie, Mark Riedl] [Prompt Engineering] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-9-blue)]() \n- `ArXiv-2023` **EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08185) [Wang You, Wenshan Wu, Yaobo Liang, Shaoguang Mao, Chenfei Wu, Maosong Cao, Yuzhe Cai, Yiduo Guo, Yan Xia, Furu Wei, Nan Duan] [Prompt Engineering] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-9-blue)]() \n\n### Multi Agent\n- `ICLR-2026` **HAMLET: A Hierarchical and Adaptive Multi-Agent Framework for Live Embodied Theatrics**  [Shufan Jiang, Sizhou Chen, Chi Zhang, Xiao-Lei Zhang, Xuelong Li] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpaper-OpenReview-b31b1b?color=b31b1b&logo=arxiv&logoColor=white)](https:\u002F\u002Fopenreview.net\u002Fpdf?id=MKwW04UHW1) [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGitHub-Code-blue?logo=github&logoColor=white)](https:\u002F\u002Fgithub.com\u002FTsumugii24\u002FHAMLET) [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20HuggingFace-Dataset-ffc107?color=ffc107&logoColor=white)](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FTsumugii\u002FHAMLET)\n- `ArXiv-2025` **A Cognitive Writing Perspective for Constrained Long-Form Text Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.12568) [Kaiyang Wan, Honglin Mu, Rui Hao, Haoran Luo, Tianle Gu, Xiuying Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `ICLR-2025` **Agents' Room: Narrative Generation through Multi-step Collaboration** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.02603) [Fantine Huot, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark, Mirella Lapata] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-16-blue)]()\n- `ACL-2024` **IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01093) [Senyu Han, Lu Chen, Li-Min Lin, Zhengshan Xu, Kai Yu] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-16-blue)]()\n- `EMNLP Findings-2024` **HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.11683) [Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Rongsheng Zhang, Yujiu Yang, Tian Feng] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-9-blue)]()\n- `FDG-2024` **StoryVerse: Towards Co-authoring Dynamic Plot with LLM-based Character Simulation via Narrative Planning** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.13042) [Yi Wang, Qian Zhou, David Ledo] [virtual characters] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-14-blue)]() \n- `IJCAI-2024` **AutoAgents: A Framework for Automatic Agent Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.17288) [Guangyao Chen, Siwei Dong, Yu Shu, Ge Zhang, Jaward Sesay, Börje F. Karlsson, Jie Fu, Yemin Shi] [Prompt Engineering] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-129-blue)]()\n\n### Multimodality\n- `ArXiv-2024` **SEED-Story: Multimodal Long Story Generation with Large Language Model** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.08683) [Shuai Yang, Yuying Ge, Yang Li, Yukang Chen, Yixiao Ge, Ying Shan, Yingcong Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-55-blue)]()\n- `CVPR-2023` **Make-A-Story: Visual Memory Conditioned Consistent Story Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.13319) [Tanzila Rahman, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Shweta Mahajan, Leonid Sigal] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-84-blue)]()\n\n### Better Storytelling\n- `ArXiv-2025` **All Stories Are One Story: Emotional Arc Guided Procedural Game Level Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.02132) [Yunge Wen, Chenliang Huang, Hangyu Zhou, Zhuo Zeng, Chun Ming Louis Po, Julian Togelius, Timothy Merino, Sam Earle] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-2-blue)]()\n- `ArXiv-2025` **Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.11900) [Kabir Ahuja, Melanie Sclar, Yulia Tsvetkov] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `ArXiv-2025` **Learning to Reason for Long-Form Story Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.22828) [Alexander Gurung, Mirella Lapata] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `ArXiv-2024` **MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.02897) [Jinming Zhang, Yunfei Long] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `EMNLP Findings-2024` **SWAG: Storytelling With Action Guidance** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03483) [Zeeshan Patel, Karim El-Refai, Jonathan Pei, Tianle Li] [Reinforcement learning \u002F SFT] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]() \n- `EMNLP Findings-2023` **Improving Pacing in Long-Form Story Planning** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.04459) [Yichen Wang, Kevin Yang, Xiaoming Liu, Dan Klein] [Story pacing] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-19-blue)]() \n- `ArXiv-2023` **End-to-End Story Plot Generator** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08796) [Hanlin Zhu, Andrew Cohen, Danqing Wang, Kevin Yang, Xiaomeng Yang, Jiantao Jiao, Yuandong Tian] [SFT] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]() \n- `EMNLP Findings-2023` **GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05388) [Zhihua Wen, Zhiliang Tian, Wei Wu, Yuxin Yang, Yanqi Shi, Zhen Huang, Dongsheng Li] [RAG] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-14-blue)]() \n\n### More Controllable\n- `ArXiv-2025` **SCORE: Story Coherence and Retrieval Enhancement for AI Narratives** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.23512) [Qiang Yi, Yangfan He, Jianhui Wang, Xinyuan Song, Shiyao Qian, Miao Zhang, Li Sun, Tianyu Shi] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-17-blue)]()\n- `AIIDE-2024` **NarrativeGenie: Generating Narrative Beats and Dynamic Storytelling with Large Language Models** [[paper]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAIIDE\u002Farticle\u002Fview\u002F31868) [Vikram Kumaran, Jonathan Rowe, James Lester] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-16-blue)]()\n- `ArXiv-2024` **Crafting Narrative Closures: Zero-Shot Learning with SSM Mamba for Short Story Ending Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.10848) [Divyam Sharma, Divya Santhanam] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ACL-2024` **MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.05690)  [[code]](https:\u002F\u002Fgithub.com\u002FGAIR-NLP\u002FMoPS) [Yan Ma, Yu Qiao, Pengfei Liu] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `ArXiv-2024` **Multigenre AI-powered Story Composition** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.06685v2) [Edirlei Soares de Lima, Margot M. E. Neggers, Antonio L. Furtado] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `NAACL-2024` **Returning to the Start: Generating Narratives with Related Endpoints** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.00829) [[code]](https:\u002F\u002Fgithub.com\u002Fadbrei\u002FRENarGen) [Anneliese Brei, Chao Zhao, Snigdha Chaturvedi] [SFT \u002F Prompt Engineering] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]() \n- `COLM-2024` **With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.11504) [Y. Wang, D. Ma, D. Cai] [LoRA] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-20-blue)]()\n- `ICLR-2024` **RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.12950) [Kevin Yang, Dan Klein, Asli Celikyilmaz, Nanyun Peng, Yuandong Tian] [Reinforcement learning] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-24-blue)]() \n- `ArXiv-2023` **RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.13304) [[code]](https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002FRecurrentGPT) [Wangchunshu Zhou, Yuchen Eleanor Jiang, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell, Mrinmaya Sachan] [Prompt Engineering] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-64-blue)]() \n\n### More Personalized\n- `ArXiv-2025` **STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.03547) [Eric Zhou, Shreyas Basavatia, Moontashir Siam, Zexin Chen, Mark O. Riedl] [Game] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ICLR-2025` **R^2: A LLM BASED NOVEL-TO-SCREENPLAY GENERATION FRAMEWORK WITH CAUSAL PLOT GRAPHS** [[paper]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2503.15655) [Zefeng Lin, Yi Xiao, Zhiqiang Mo, Qifan Zhang, Jie Wang, Jiayang Chen, Jiajing Zhang, Hui Zhang, Zhengyi Liu, Xianyong Fang, Xiaohua Xu] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **Towards Enhanced Immersion and Agency for LLM-based Interactive Drama** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.17878) [Hongqiu Wu, Weiqi Wu, Tianyang Xu, Jiameng Zhang, Hai Zhao] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.15616) [Xueran Han, Yuhan Liu, Mingzhe Li, Wei Liu, Sen Hu, Rui Yan, Zhiqiang Xu, Xiuying Chen] [Style] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **Whose story is it? Personalizing story generation by inferring author styles** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.13028) [Nischal Ashok Kumar, Chau Minh Pham, Mohit Iyyer, Andrew Lan] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `EMNLP-2024` **MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.13935) [Sarfaroz Yunusov, Hamza Sidat, Ali Emami] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2024` **CAT-LLM: Prompting Large Language Models with Text Style Definition for Chinese Article-style Transfer** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.05707) [Zhen Tao, Dinghao Xi, Zhiyu Li, Liumin Tang, Wei Xu] [Style] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-13-blue)]() \n- `ArXiv-2023` **Learning to Generate Text in Arbitrary Writing Styles** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.17242) [Aleem Khan, Andrew Wang, Sophia Hager, Nicholas Andrews] [Style] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]() \n\n### Evaluation\n- `ICCV AISTORY Workshop-2025` **Re:Verse -- Can Your VLM Read a Manga?** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.08508) [Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, Shruti Vyas] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.17136) [Brihi Joshi, Sriram Venkatapathy, Mohit Bansal, Nanyun Peng, Haw-Shiuan Chang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19103) [Siwei Wu, Yizhi Li, Xingwei Qu, Rishi Ravikumar, Yucheng Li, Tyler Loakman, Shanghaoran Quan, Xiaoyong Wei, Riza Batista-Navarro, Chenghua Lin] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `ArXiv-2025` **Echoes in AI: Quantifying Lack of Plot Diversity in LLM Outputs** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.00273) [Weijia Xu, Nebojsa Jojic, Sudha Rao, Chris Brockett, Bill Dolan] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `ArXiv-2024` **Evaluating Creative Short Story Generation in Humans and Large Language Models** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.02316) [Mete Ismayilzada, Claire Stevenson, Lonneke van der Plas] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]()\n- `ArXiv-2024` **CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.04197) [Anirudh Atmakuru, Jatin Nainani, Rohith Siddhartha Reddy Bheemreddy, Anirudh Lakkaraju, Zonghai Yao, Hamed Zamani, Haw-Shiuan Chang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `COLING-2025` **Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.11547) [Guillermo Marco, Luz Rello, Julio Gonzalo] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `NAACL-2025` **FACTTRACK: Time-Aware World State Tracking in Story Outlines** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.16347) [Zhiheng Lyu, Kevin Yang, Lingpeng Kong, Daniel Klein] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `EMNLP-2024` **Are Large Language Models Capable of Generating Human-Level Narratives?** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.13248) [Yufei Tian, Tenghao Huang, Miri Liu, Derek Jiang, Alexander Spangher, Muhao Chen, Jonathan May, Nanyun Peng] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-33-blue)]()\n- `EMNLP-2024` **STORYSUMM: Evaluating Faithfulness in Story Summarization** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.06501) [Melanie Subbiah, Faisal Ladhak, Akankshya Mishra, Griffin Adams, Lydia B. Chilton, Kathleen McKeown] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `ArXiv-2024` **Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01119) [Guillermo Marco, Julio Gonzalo, Ramón del Castillo, María Teresa Mateo Girona] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-17-blue)]()\n- `EMNLP-2024` **Measuring Psychological Depth in Language Models** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.12680) [Fabrice Harel-Canada, Hanyu Zhou, Sreya Muppalla, Zeynep Yildiz, Miryung Kim, Amit Sahai, Nanyun Peng] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `TACL-2024` **Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.13769) [Cyril Chhun, Fabian M. Suchanek, Chloé Clavel] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-18-blue)]()\n- `TACL-2024` **Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.01061) [Melanie Subbiah, Sean Zhang, Lydia B. Chilton, Kathleen McKeown] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-15-blue)]()\n- `EMNLP Findings-2023` **A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08433) [Carlos Gómez-Rodríguez, Paul Williams] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-83-blue)]()\n- `EMNLP-2024` **Learning Personalized Alignment for Evaluating Open-ended Text Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.03304) [Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-11-blue)]()\n- `ICLR-2024` **BooookScore: A systematic exploration of book-length summarization in the era of LLMs**[[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.00785)[Yapei Chang, Kyle Lo, Tanya Goyal, Mohit Iyyer] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-117-blue)]()\n- `TMLR-2024` **TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks**[[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.00752)[Dongfu Jiang, Yishan Li, Ge Zhang, Wenhao Huang, Bill Yuchen Lin, Wenhu Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-69-blue)]()\n- `CHI-2023` **Art or Artifice? Large Language Models and the False Promise of Creativity** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.14556) [Tuhin Chakrabarty, Philippe Laban, Divyansh Agarwal, Smaranda Muresan, Chien-Sheng Wu]   [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-136-blue)]()\n- `ACL-2023` **HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.07554) [Qianyu He, Yikai Zhang, Jiaqing Liang, Yuncheng Huang, Yanghua Xiao, Yunwen Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `ACL-2023` **Can Large Language Models Be an Alternative to Human Evaluations?** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.01937) [Cheng-Han Chiang, Hung-yi Lee] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-634-blue)]()\n- `EMNLP Findings-2023` **DeltaScore: Evaluating Story Generation with Differentiating Perturbations** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.08991) [Zhuohan Xie, Miao Li, Trevor Cohn, Jey Han Lau] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `EMNLP-2022` **StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.08459) [Hong Chen, Duc Minh Vo, Hiroya Takamura, Yusuke Miyao, Hideki Nakayama] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-20-blue)]()\n- `COLING-2022` **Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2208.11646)  [Cyril Chhun, Pierre Colombo, Chloé Clavel, Fabian M. Suchanek] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-55-blue)]()\n- `TACL-2022` **LOT: A story-centric benchmark for evaluating Chinese long text understanding and generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.12960) [Jian Guan, Zhuoer Feng, Yamei Chen, Ruilin He, Xiaoxi Mao, Changjie Fan, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-33-blue)]()\n- `ACL-2021` **Openmeva: A benchmark for evaluating open-ended story generation metrics** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.08920) [Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-61-blue)]()\n- `EMNLP-2020` **Union: An unreferenced metric for evaluating open-ended story generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.07602) [[code]](https:\u002F\u002Fgithub.com\u002Fthu-coai\u002FUNION) [Jian Guan, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-70-blue)]()\n\n\n### Dataset\n- `EMNLP Findings-2024` **BookWorm: A Dataset for Character Description and Analysis** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.10372) [Argyrios Papoudakis, Mirella Lapata, Frank Keller] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-2-blue)]()\n- `EMNLP Workshop-2025` **The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.16767) [Xi Yu Huang, Krishnapriya Vishnubhotla, Frank Rudzicz] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `NAACL Findings-2025` **CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysis** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.12665) [Saranya Venkatraman, Nafis Irtiza Tripto, Dongwon Lee]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-14-blue)]()\n- `ACL Findings-2024` **Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.11051) [Runcong Zhao, Qinglin Zhu, Hainiu Xu, Jiazheng Li, Yuxiang Zhou, Yulan He, Lin Gui] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-13-blue)]()\n- `LREC-COLING-2024` **CLAUSE-ATLAS: A Corpus of Narrative Information to Scale up Computational Literary Analysis** [[paper]](https:\u002F\u002Faclanthology.org\u002F2024.lrec-main.292\u002F) [Enrica Troiano, Piek T.J.M. Vossen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `LREC-COLING-2024` **Reflections & Resonance: Two-Agent Partnership for Advancing LLM-based Story Annotation** [[paper]](https:\u002F\u002Faclanthology.org\u002F2024.lrec-main.1206\u002F) [Yuetian Chen, Mei Si]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `LREC-COLING-2024` **CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.13145) [Yujie Shao, Xinrong Yao, Xingwei Qu, Chenghua Lin, Shi Wang, Stephen W. Huang, Ge Zhang, Jie Fu]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `ArXiv-2023` **STONYBOOK: A System and Resource for Large-Scale Analysis of Novels** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.03614) [Charuta Pethe, Allen Kim, Rajesh Prabhakar, Tanzir Pial, Steven Skiena] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `ACL-2023` **StoryWars: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.08152) [Yulun Du, Lydia Chilton] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-8-blue)]()\n- `NAACL-2022` **A corpus for understanding and generating moral stories** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.09438) [Jian Guan, Ziqi Liu, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-10-blue)]()\n- `EVAL4NLP-2021` **StoryDB: Broad Multi-language Narrative Dataset** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.14396) [Alexey Tikhonov, Igor Samenko, Ivan P. Yamshchikov] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]()\n- `ACL-2022` **SummScreen: A Dataset for Abstractive Screenplay Summarization** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.07091) [[data]](https:\u002F\u002Fgithub.com\u002Fmingdachen\u002FSummScreen) [Mingda Chen, Zewei Chu, Sam Wiseman, Kevin Gimpel] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-96-blue)]() \n- `ArXiv-2021` **TVStoryGen: A Dataset for Generating Stories with Character Descriptions** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.08833) [Mingda Chen, Kevin Gimpel] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]() \n- `EMNLP-2020` **STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.01717) [Nader Akoury, Shufan Wang, Josh Whiting, Stephen Hood, Nanyun Peng, Mohit Iyyer] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-88-blue)]()\n- `NAACL-2016` **A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories** [[paper]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1604.01696) [Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, James Allen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-713-blue)]()\n\n\n## Public Resources\n- [Understanding AI for Stories](https:\u002F\u002Fisamu-website.medium.com\u002Funderstanding-ai-for-stories-d0c1cd7b7bdc) serves as a survey blog that delves into the application of AI in the realm of story generation, shedding light on its potential as well as the challenges that it encounters.\n- [ROC Stories](https:\u002F\u002Fcs.rochester.edu\u002Fnlp\u002Frocstories\u002F) is a compilation of 100,000 five-sentence stories and 3,742 Story Cloze Test stories, capturing a rich array of causal and temporal commonsense connections between everyday events, making it suitable for story generation tasks.\n- [CommonGen](https:\u002F\u002Finklab.usc.edu\u002FCommonGen\u002F) was developed by combining crowdsourced and existing caption corpora, containing 79k commonsense descriptions across 35k distinct concept-sets.\n- [CMU Movie Summary Corpus](http:\u002F\u002Fwww.cs.cmu.edu\u002F~ark\u002Fpersonas\u002F) offers access to a dataset containing movie plot summaries and related metadata.\n- [Scifi TV Show Plot Summaries & Events](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Flara-martin\u002FScifi_TV_Shows) is a collection of plot synopses for long-running (80+ episodes) science fiction TV shows, sourced from Fandom.com wikis.\n\n![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyingpengma_Awesome-Story-Generation_readme_1bfec4ffe525.png)\n","\u003Ch1 align=\"center\">超棒的故事生成\u003C\u002Fh1>\n\n\u003Cdiv align=\"center\">由 \u003Ca href=\"https:\u002F\u002Fyingpengma.github.io\u002F\">Yingpeng Ma\u003C\u002Fa> 和 \u003Ca href=\"https:\u002F\u002Fmantle2048.github.io\u002F\">Yan Ma\u003C\u002Fa> 贡献\u003C\u002Fdiv>\n\n##\n\n🔥 认识到**大型语言模型**带来的范式转变，我们现在专注于与LLM相关的研究。\n\n对于那些对LLM时代之前的研究感兴趣的人，可以在[旧版本](old_version.md)中找到归档版本（该归档版本已**不再维护**）。\n\n## 目录\n\n- [简介](#introduction)\n\u003C!--\n- [相关仓库](#related-repository)\n-->\n- [论文](#papers)\n  - [概述](#overview)\n  - [规划与写作](#plan-and-write)\n  - [多智能体](#multi-agent)\n  - [多模态](#multimodality)\n  - [更好的讲故事](#better-storytelling)\n  - [更可控](#more-controllable)\n  - [更个性化](#more-personalized)\n  - [评估](#evaluation)\n  - [数据集](#dataset)\n- [公共资源](#public-resources)\n\n## 简介\n\n本仓库收集了LLM时代关于**故事生成\u002F讲故事**的优秀论文。\n\n论文按时间顺序排列（最新的在前）。\n\n**感谢大家的点赞！** 我们会持续更新最新的研究成果。干杯！🍻\n\n您的贡献非常重要！请通过提交issue或pull request来帮助我们保持这份列表的最新和准确，以纠正任何错误或补充遗漏的论文。\n\n联系方式：`mayingpeng33 [AT] gmail [DOT] com`\n\n\u003C!--\n## 相关仓库\n|**[超棒的LLM角色](https:\u002F\u002Fgithub.com\u002Fyingpengma\u002FAwesome-LLM-Characters)**|\n|:---:|\n-->\n\n## 论文\n例如：`ACL-20XX` **标题** [论文] [代码] .. [作者]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-count-blue)]()\n\n### 概述\n- `ArXiv-2024` **什么构成一个好的故事？我们如何衡量它？故事评估的全面综述** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.14622) [Dingyi Yang, Qin Jin] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `CHI-2024` **生成式AI辅助写作的价值、好处与担忧** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.12004) [Zhuoyan Li, Chen Liang, Jing Peng, Ming Yin] [主要讨论ChatGPT，未涉及其他模型] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-59-blue)]() \n- `ArXiv-2024` **Weaver：用于创意写作的基础模型** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.17268) [Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, ... , Yuchen Eleanor Jiang, Wangchunshu Zhou] [专注于写作能力的基础模型] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-20-blue)]()\n- `Neurocomputing-2023` **基于结构化知识增强的开放世界故事生成：全面综述** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.04634) [Yuxin Wang, Jieru Lin, Zhiwei Yu, Wei Hu, Börje F. Karlsson] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-39-blue)]()\n- `EMNLP Findings-2023` **NLP模型擅长追踪思维吗？叙事理解的概述** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.18783) [Lixing Zhu, Runcong Zhao, Lin Gui, Yulan He] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]()\n\n### 规划与写作\n- `ArXiv-2025` **学习推理以进行长篇故事生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.22828v2) [Alexander Gurung, Mirella Lapata] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `NAACL-2025` **利用动态层次大纲与记忆增强生成长篇故事** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.13575) [Qianyue Wang, Jinwu Hu, Zhengping Li, Yufeng Wang, daiyuan li, Yu Hu, Mingkui Tan] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `EMNLP-2024` **集体评论家助力创意故事生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.02428) [Minwook Bae, Hyounghun Kim] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `ACL-2024` **Ex3：通过提取、提炼与扩展实现自动小说写作** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.08506) [Lei Huang, Jiaming Guo, Guanhua He, Xishan Zhang, Rui Zhang, Shaohui Peng, Shaoli Liu, Tianshi Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-2-blue)]()\n- `ACL Workshop-2025` **通过答案集编程引导并多样化基于LLM的故事生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.00554) [Phoebe J. Wang, Max Kreminski] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `NAACL-2025` **书写之路：大型语言模型指导下的提纲式文本生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.13919) [Yukyung Lee, Soonwon Ka, Bokyung Son, Pilsung Kang, Jaewook Kang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `EACL-2024` **创作悬疑故事：利用大型语言模型进行迭代式规划** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.17119) [Kaige Xie, Mark Riedl] [提示工程] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-9-blue)]() \n- `ArXiv-2023` **EIPE-text：评估引导的迭代式计划提取，用于长篇叙事文本生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08185) [Wang You, Wenshan Wu, Yaobo Liang, Shaoguang Mao, Chenfei Wu, Maosong Cao, Yuzhe Cai, Yiduo Guo, Yan Xia, Furu Wei, Nan Duan] [提示工程] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-9-blue)]()\n\n### 多智能体\n- `ICLR-2026` **HAMLET：用于实时具身戏剧表演的分层自适应多智能体框架**  [江书凡、陈思舟、张驰、张晓雷、李学龙] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpaper-OpenReview-b31b1b?color=b31b1b&logo=arxiv&logoColor=white)](https:\u002F\u002Fopenreview.net\u002Fpdf?id=MKwW04UHW1) [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGitHub-Code-blue?logo=github&logoColor=white)](https:\u002F\u002Fgithub.com\u002FTsumugii24\u002FHAMLET) [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20HuggingFace-Dataset-ffc107?color=ffc107&logoColor=white)](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FTsumugii\u002FHAMLET)\n- `ArXiv-2025` **面向约束长文本生成的认知写作视角** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.12568) [万凯阳、穆洪林、郝睿、罗浩然、顾天乐、陈秀英] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `ICLR-2025` **Agent's Room：通过多步协作进行叙事生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.02603) [芳汀·于奥、雷纳尔德·金·安普拉约、珍妮玛丽亚·帕洛马基、爱丽丝·肖莎娜·雅各博维茨、伊丽莎白·克拉克、米雷拉·拉帕塔] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-16-blue)]()\n- `ACL-2024` **IBSEN：导演-演员智能体协作，用于可控且交互式的戏剧剧本生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01093) [韩森宇、陈璐、林丽敏、徐正山、余凯] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-16-blue)]()\n- `EMNLP Findings-2024` **HoLLMwood：通过角色扮演释放大语言模型在编剧中的创造力** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.11683) [陈静、朱欣宇、杨成、石楚凡、奚亚东、张宇翔、王俊杰、蒲家树、张荣生、杨宇久、冯田] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-9-blue)]()\n- `FDG-2024` **StoryVerse：基于LLM的角色模拟与叙事规划，实现动态情节的共同创作** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.13042) [王毅、周倩、大卫·莱多] [虚拟角色] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-14-blue)]()\n- `IJCAI-2024` **AutoAgents：自动智能体生成框架** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.17288) [陈光耀、董思伟、舒宇、张戈、贾瓦德·塞塞、博尔耶·F·卡尔松、傅杰、史叶民] [提示工程] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-129-blue)]()\n\n### 多模态\n- `ArXiv-2024` **SEED-Story：基于大语言模型的多模态长篇故事生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.08683) [杨帅、葛雨莹、李洋、陈宇康、葛一骁、单颖、陈迎聪] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-55-blue)]()\n- `CVPR-2023` **Make-A-Story：视觉记忆条件下的连贯故事生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.13319) [坦齐拉·拉赫曼、李欣颖、任健、谢尔盖·图利亚科夫、什韦塔·马哈詹、列昂尼德·西格尔] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-84-blue)]()\n\n### 更好的叙事\n- `ArXiv-2025` **所有故事都是一个故事：情感弧线引导的程序化游戏关卡生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.02132) [温云格、黄晨亮、周航宇、曾卓、路易斯·陈明、朱利安·托格利乌斯、蒂莫西·梅里诺、萨姆·厄尔] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-2-blue)]()\n- `ArXiv-2025` **寻找有缺陷的小说：通过情节漏洞检测评估语言模型的复杂推理能力** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.11900) [卡比尔·阿胡贾、梅拉妮·斯克拉、尤莉娅·茨维特科娃] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `ArXiv-2025` **为长篇故事生成而学习推理** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.22828) [亚历山大·古隆、米雷拉·拉帕塔] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `ArXiv-2024` **MLD-EA：通过引入情感和行动来检查并完善叙事连贯性** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.02897) [张锦明、龙云飞] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `EMNLP Findings-2024` **SWAG：以行动为导向的故事叙述** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03483) [泽山·帕特尔、卡里姆·埃尔-里法伊、乔纳森·裴、李天乐] [强化学习 \u002F SFT] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]() \n- `EMNLP Findings-2023` **改进长篇故事规划中的节奏控制** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.04459) [王义辰、杨凯文、刘晓明、丹·克莱因] [故事节奏] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-19-blue)]() \n- `ArXiv-2023` **端到端故事剧情生成器** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08796) [朱汉林、安德鲁·科恩、王丹青、杨凯文、杨晓梦、焦建涛、田元东] [SFT] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]() \n- `EMNLP Findings-2023` **GROVE：一种基于证据森林的检索增强型复杂故事生成框架** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05388) [文志华、田志良、吴伟、杨宇鑫、施燕琪、黄振、李东升] [RAG] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-14-blue)]()\n\n### 更具可控性\n- `ArXiv-2025` **SCORE：用于AI叙事的故事连贯性与检索增强** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.23512) [Yi Qiang, He Yangfan, Wang Jianhui, Song Xinyuan, Qian Shiyao, Zhang Miao, Sun Li, Shi Tianyu] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-17-blue)]()\n- `AIIDE-2024` **NarrativeGenie：利用大型语言模型生成叙事片段与动态叙事** [[论文]](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAIIDE\u002Farticle\u002Fview\u002F31868) [Kumaran Vikram, Rowe Jonathan, Lester James] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-16-blue)]()\n- `ArXiv-2024` **构建叙事结局：基于SSM Mamba的零样本学习用于短篇小说结尾生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.10848) [Sharma Divyam, Santhanam Divya] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ACL-2024` **MoPS：用于开放式自动故事生成的模块化故事前提合成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.05690) [[代码]](https:\u002F\u002Fgithub.com\u002FGAIR-NLP\u002FMoPS) [Ma Yan, Qiao Yu, Liu Pengfei] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `ArXiv-2024` **多类型AI驱动的故事创作** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.06685v2) [Soares de Lima Edirlei, Neggers Margot M. E., Furtado Antonio L.] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `NAACL-2024` **回到起点：生成具有相关终点的叙事** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.00829) [[代码]](https:\u002F\u002Fgithub.com\u002Fadbrei\u002FRENarGen) [Brei Anneliese, Zhao Chao, Chaturvedi Snigdha] [SFT \u002F 提示工程] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `COLM-2024` **文本越长，需求越大：推理时训练助力长文本生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.11504) [Wang Y., Ma D., Cai D.] [LoRA] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-20-blue)]()\n- `ICLR-2024` **RLCD：基于对比蒸馏的强化学习用于语言模型对齐** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.12950) [Yang Kevin, Klein Dan, Celikyilmaz Asli, Peng Nanyun, Tian Yuandong] [强化学习] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-24-blue)]()\n- `ArXiv-2023` **RecurrentGPT：交互式生成（任意长度）文本** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.13304) [[代码]](https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002FRecurrentGPT) [Zhou Wangchunshu, Jiang Yuchen Eleanor, Cui Peng, Wang Tiannan, Xiao Zhenxin, Hou Yifan, Cotterell Ryan, Sachan Mrinmaya] [提示工程] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-64-blue)]()\n\n### 更具个性化\n- `ArXiv-2025` **STORY2GAME：在互动式小说游戏中生成（几乎）一切** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.03547) [Zhou Eric, Basavatia Shreyas, Siam Moontashir, Chen Zexin, Riedl Mark O.] [游戏] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ICLR-2025` **R^2：基于LLM的小说到剧本生成框架，结合因果剧情图** [[论文]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2503.15655) [Lin Zefeng, Xiao Yi, Mo Zhiqiang, Zhang Qifan, Wang Jie, Chen Jiayang, Zhang Jiajing, Zhang Hui, Liu Zhengyi, Fang Xianyong, Xu Xiaohua] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **迈向增强沉浸感与自主性的基于LLM的互动戏剧** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.17878) [Wu Hongqiu, Wu Weiqi, Xu Tianyang, Zhang Jiameng, Zhao Hai] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **拼贴式小说生成：以你喜爱的作家风格创作同人小说** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.15616) [Han Xueran, Liu Yuhan, Li Mingzhe, Liu Wei, Hu Sen, Yan Rui, Xu Zhiqiang, Chen Xiuying] [风格] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **这是谁的故事？通过推断作者风格实现故事生成的个性化** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.13028) [Ashok Kumar Nischal, Pham Chau Minh, Iyyer Mohit, Lan Andrew] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `EMNLP-2024` **MirrorStories：通过大型语言模型的个性化叙事生成反映多样性** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.13935) [Yunusov Sarfaroz, Sidat Hamza, Emami Ali] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2024` **CAT-LLM：以文本风格定义为提示，实现中文文章风格迁移的大型语言模型应用** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.05707) [Tao Zhen, Xi Dinghao, Li Zhiyu, Tang Liumin, Xu Wei] [风格] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-13-blue)]()\n- `ArXiv-2023` **学习生成任意写作风格的文本** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.17242) [Khan Aleem, Wang Andrew, Hager Sophia, Andrews Nicholas] [风格] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n\n### 评估\n- `ICCV AISTORY Workshop-2025` **Re:Verse -- 您的多模态语言模型能读懂漫画吗？** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.08508) [Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, Shruti Vyas] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **CoKe：基于关键词推理链的可定制细粒度故事评估** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.17136) [Brihi Joshi, Sriram Venkatapathy, Mohit Bansal, Nanyun Peng, Haw-Shiuan Chang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `ArXiv-2025` **LongEval：基于规划范式的长文本生成综合分析** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19103) [Siwei Wu, Yizhi Li, Xingwei Qu, Rishi Ravikumar, Yucheng Li, Tyler Loakman, Shanghaoran Quan, Xiaoyong Wei, Riza Batista-Navarro, Chenghua Lin] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `ArXiv-2025` **AI中的回声：量化大语言模型输出中情节多样性的不足** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.00273) [Weijia Xu, Nebojsa Jojic, Sudha Rao, Chris Brockett, Bill Dolan] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `ArXiv-2024` **人类与大型语言模型在创意短篇小说生成方面的评估** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.02316) [Mete Ismayilzada, Claire Stevenson, Lonneke van der Plas] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]()\n- `ArXiv-2024` **CS4：通过控制故事写作约束的数量自动衡量大型语言模型的创造力** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.04197) [Anirudh Atmakuru, Jatin Nainani, Rohith Siddhartha Reddy Bheemreddy, Anirudh Lakkaraju, Zonghai Yao, Hamed Zamani, Haw-Shiuan Chang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `COLING-2025` **小型语言模型在短篇创意写作方面可超越人类：小型语言模型与人类及大型语言模型的比较研究** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.11547) [Guillermo Marco, Luz Rello, Julio Gonzalo] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-7-blue)]()\n- `NAACL-2025` **FACTTRACK：故事大纲中的时间感知世界状态追踪** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.16347) [Zhiheng Lyu, Kevin Yang, Lingpeng Kong, Daniel Klein] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `EMNLP-2024` **大型语言模型能否生成达到人类水平的叙事？** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.13248) [Yufei Tian, Tenghao Huang, Miri Liu, Derek Jiang, Alexander Spangher, Muhao Chen, Jonathan May, Nanyun Peng] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-33-blue)]()\n- `EMNLP-2024` **STORYSUMM：评估故事摘要的忠实性** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.06501) [Melanie Subbiah, Faisal Ladhak, Akankshya Mishra, Griffin Adams, Lydia B. Chilton, Kathleen McKeown] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `ArXiv-2024` **Pron vs Prompt：大型语言模型是否已能在创意文本写作上挑战世界级小说家？** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.01119) [Guillermo Marco, Julio Gonzalo, Ramón del Castillo, María Teresa Mateo Girona] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-17-blue)]()\n- `EMNLP-2024` **衡量语言模型的心理深度** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.12680) [Fabrice Harel-Canada, Hanyu Zhou, Sreya Muppalla, Zeynep Yildiz, Miryung Kim, Amit Sahai, Nanyun Peng] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `TACL-2024` **语言模型会喜欢自己的故事吗？通过提示引导大型语言模型进行自动故事评估** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.13769) [Cyril Chhun, Fabian M. Suchanek, Chloé Clavel] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-18-blue)]()\n- `TACL-2024` **解读潜台词：与作家共同评估大型语言模型的短篇小说摘要能力** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.01061) [Melanie Subbiah, Sean Zhang, Lydia B. Chilton, Kathleen McKeown] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-15-blue)]()\n- `EMNLP Findings-2023` **模型联盟：对大型语言模型创意写作能力的全面评估** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08433) [Carlos Gómez-Rodríguez, Paul Williams] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-83-blue)]()\n- `EMNLP-2024` **用于开放式文本生成评估的个性化对齐学习** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.03304) [Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-11-blue)]()\n- `ICLR-2024` **BooookScore：大语言模型时代下书本级摘要的系统性探索**[[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.00785)[Yapei Chang, Kyle Lo, Tanya Goyal, Mohit Iyyer] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-117-blue)]()\n- `TMLR-2024` **TIGERScore：迈向所有文本生成任务的可解释性评估指标**[[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.00752)[Dongfu Jiang, Yishan Li, Ge Zhang, Wenhao Huang, Bill Yuchen Lin, Wenhu Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-69-blue)]()\n- `CHI-2023` **艺术还是人工？大型语言模型与创造力的虚假承诺** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.14556) [Tuhin Chakrabarty, Philippe Laban, Divyansh Agarwal, Smaranda Muresan, Chien-Sheng Wu] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-136-blue)]()\n- `ACL-2023` **HAUSER：迈向比喻生成的全面自动化评估** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.07554) [Qianyu He, Yikai Zhang, Jiaqing Liang, Yuncheng Huang, Yanghua Xiao, Yunwen Chen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `ACL-2023` **大型语言模型能否替代人工评估？** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.01937) [Cheng-Han Chiang, Hung-yi Lee] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-634-blue)]()\n- `EMNLP Findings-2023` **DeltaScore：通过差异化扰动评估故事生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.08991) [Zhuohan Xie, Miao Li, Trevor Cohn, Jey Han Lau] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-4-blue)]()\n- `EMNLP-2022` **StoryER：通过排名、评分和推理实现故事的自动评估** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.08459) [Hong Chen, Duc Minh Vo, Hiroya Takamura, Yusuke Miyao, Hideki Nakayama] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-20-blue)]()\n- `COLING-2022` **人类标准与自动指标：故事生成评估的基准测试** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2208.11646) [Cyril Chhun, Pierre Colombo, Chloé Clavel, Fabian M. Suchanek] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-55-blue)]()\n- `TACL-2022` **LOT：一个以故事为中心的基准，用于评估中文长文本理解和生成** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.12960) [Jian Guan, Zhuoer Feng, Yamei Chen, Ruilin He, Xiaoxi Mao, Changjie Fan, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-33-blue)]()\n- `ACL-2021` **Openmeva：开放式故事生成评估指标的基准测试** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.08920) [Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-61-blue)]()\n- `EMNLP-2020` **Union：一种未引用的开放式故事生成评估指标** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.07602) [[代码]](https:\u002F\u002Fgithub.com\u002Fthu-coai\u002FUNION) [Jian Guan, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-70-blue)]()\n\n### 数据集\n- `EMNLP Findings-2024` **BookWorm：用于人物描述与分析的数据集** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.10372) [Argyrios Papoudakis, Mirella Lapata, Frank Keller] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-2-blue)]()\n- `EMNLP Workshop-2025` **GPT-WritingPrompts数据集：短篇小说中人物刻画的比较分析** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.16767) [Xi Yu Huang, Krishnapriya Vishnubhotla, Frank Rudzicz] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-3-blue)]()\n- `NAACL Findings-2025` **CollabStory：多大语言模型协作生成故事及作者身份分析** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.12665) [Saranya Venkatraman, Nafis Irtiza Tripto, Dongwon Lee]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-14-blue)]()\n- `ACL Findings-2024` **大型语言模型表现不足：理解侦探叙事中的复杂关系** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.11051) [Runcong Zhao, Qinglin Zhu, Hainiu Xu, Jiazheng Li, Yuxiang Zhou, Yulan He, Lin Gui] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-13-blue)]()\n- `LREC-COLING-2024` **CLAUSE-ATLAS：用于扩展计算文学分析的叙事信息语料库** [[论文]](https:\u002F\u002Faclanthology.org\u002F2024.lrec-main.292\u002F) [Enrica Troiano, Piek T.J.M. Vossen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-0-blue)]()\n- `LREC-COLING-2024` **反思与共鸣：双智能体合作推进基于LLM的故事标注** [[论文]](https:\u002F\u002Faclanthology.org\u002F2024.lrec-main.1206\u002F) [Yuetian Chen, Mei Si]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `LREC-COLING-2024` **CMDAG：带有注释依据作为思维链的中文隐喻数据集，用于提升隐喻生成能力** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.13145) [Yujie Shao, Xinrong Yao, Xingwei Qu, Chenghua Lin, Shi Wang, Stephen W. Huang, Ge Zhang, Jie Fu]  [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-6-blue)]()\n- `ArXiv-2023` **STONYBOOK：用于大规模小说分析的系统与资源** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.03614) [Charuta Pethe, Allen Kim, Rajesh Prabhakar, Tanzir Pial, Steven Skiena] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-1-blue)]()\n- `ACL-2023` **StoryWars：用于协作式故事理解和生成的数据集及指令微调基线** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.08152) [Yulun Du, Lydia Chilton] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-8-blue)]()\n- `NAACL-2022` **用于理解和生成道德故事的语料库** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.09438) [Jian Guan, Ziqi Liu, Minlie Huang] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-10-blue)]()\n- `EVAL4NLP-2021` **StoryDB：广泛的多语言叙事数据集** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.14396) [Alexey Tikhonov, Igor Samenko, Ivan P. Yamshchikov] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]()\n- `ACL-2022` **SummScreen：用于摘要式剧本摘要生成的数据集** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.07091) [[数据]](https:\u002F\u002Fgithub.com\u002Fmingdachen\u002FSummScreen) [Mingda Chen, Zewei Chu, Sam Wiseman, Kevin Gimpel] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-96-blue)]() \n- `ArXiv-2021` **TVStoryGen：用于生成包含人物描述的故事的数据集** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.08833) [Mingda Chen, Kevin Gimpel] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-5-blue)]() \n- `EMNLP-2020` **STORIUM：人机协作式故事生成的数据集与评估平台** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.01717) [Nader Akoury, Shufan Wang, Josh Whiting, Stephen Hood, Nanyun Peng, Mohit Iyyer] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-88-blue)]()\n- `NAACL-2016` **用于更深入理解常识性故事的语料库及完形填空评估** [[论文]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1604.01696) [Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, James Allen] [![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcitation-713-blue)]()\n\n\n## 公开资源\n- [理解故事领域的AI](https:\u002F\u002Fisamu-website.medium.com\u002Funderstanding-ai-for-stories-d0c1cd7b7bdc) 是一篇综述博客，深入探讨了人工智能在故事生成领域的应用，揭示其潜力以及面临的挑战。\n- [ROC Stories](https:\u002F\u002Fcs.rochester.edu\u002Fnlp\u002Frocstories\u002F) 汇集了10万则五句故事和3,742则故事完形填空测试题，捕捉了日常事件之间丰富的因果与时间顺序常识联系，非常适合用于故事生成任务。\n- [CommonGen](https:\u002F\u002Finklab.usc.edu\u002FCommonGen\u002F) 通过整合众包和现有说明语料库而开发，包含3.5万个不同概念集合中的7.9万条常识性描述。\n- [CMU电影概要语料库](http:\u002F\u002Fwww.cs.cmu.edu\u002F~ark\u002Fpersonas\u002F) 提供了包含电影剧情概要及相关元数据的数据集访问权限。\n- [科幻电视剧剧情概要与事件](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Flara-martin\u002FScifi_TV_Shows) 是一个收集自Fandom.com维基的长期（80集以上）科幻电视剧剧情梗概的合集。\n\n![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyingpengma_Awesome-Story-Generation_readme_1bfec4ffe525.png)","# Awesome-Story-Generation 快速上手指南\n\n**Awesome-Story-Generation** 并非一个可直接安装的单一软件工具，而是一个**精选论文与资源列表**，专注于大语言模型（LLM）时代的**故事生成**（Story Generation）研究。本指南将帮助开发者快速理解该仓库结构，并指导如何基于列表中提供的具体论文代码进行环境搭建和使用。\n\n## 1. 环境准备\n\n由于本仓库汇总了多个不同的研究项目，每个项目（论文）都有独立的依赖要求。在开始之前，请确保满足以下通用前置条件：\n\n*   **操作系统**：Linux (推荐 Ubuntu 20.04+) 或 macOS。Windows 用户建议使用 WSL2。\n*   **Python 版本**：建议安装 **Python 3.9 - 3.11**（大多数 LLM 相关项目的兼容版本）。\n*   **包管理工具**：`pip` 或 `conda`（推荐用于管理不同项目的虚拟环境）。\n*   **GPU 支持**：若需运行列表中的模型代码（如 SEED-Story, HAMLET 等），需安装 NVIDIA 驱动及对应的 **CUDA**  toolkit。\n*   **Git**：用于克隆仓库及各个子项目代码。\n\n## 2. 获取资源与安装步骤\n\n本仓库本身不包含可执行代码，而是指向具体的论文实现。使用流程如下：\n\n### 第一步：克隆主仓库（查阅列表）\n首先获取论文列表和资源索引：\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fyingpengma\u002FAwesome-Story-Generation.git\ncd Awesome-Story-Generation\n```\n*提示：国内用户若访问 GitHub 较慢，可使用镜像站下载或使用 `git clone https:\u002F\u002Fghp.ci\u002Fhttps:\u002F\u002Fgithub.com\u002Fyingpengma\u002FAwesome-Story-Generation.git` 加速。*\n\n### 第二步：选择具体项目并安装\n浏览 `README.md` 中的 **Papers** 部分，找到你感兴趣的研究方向（如 `Multi Agent`, `Multimodality` 等）。点击对应条目中的 `[code]` 链接进入该论文的官方代码仓库。\n\n以列表中提到的 **HAMLET** (Multi Agent 方向) 或 **MoPS** (More Controllable 方向) 为例，通用安装步骤如下：\n\n1.  **创建虚拟环境**（避免依赖冲突）：\n    ```bash\n    conda create -n story-gen python=3.10\n    conda activate story-gen\n    ```\n\n2.  **克隆具体项目代码**（以 MoPS 为例）：\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002FGAIR-NLP\u002FMoPS.git\n    cd MoPS\n    ```\n\n3.  **安装依赖**：\n    大多数项目提供 `requirements.txt`，请使用以下命令安装（推荐配置国内 pip 源加速）：\n    ```bash\n    pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n    ```\n    *注：若项目使用 `pyproject.toml` 或 `setup.py`，请参照该项目具体的 `INSTALL.md` 说明。*\n\n4.  **下载模型权重**：\n    根据具体项目的指引，从 Hugging Face 下载预训练模型。国内用户可使用 Hugging Face 镜像：\n    ```bash\n    export HF_ENDPOINT=https:\u002F\u002Fhf-mirror.com\n    # 随后运行项目提供的下载脚本或使用 huggingface-cli\n    ```\n\n## 3. 基本使用\n\n由于每个子项目的功能不同（有的侧重长文规划，有的侧重多模态生成），使用方式需参照具体项目的 `Usage` 文档。以下是基于典型故事生成项目的**通用调用示例**：\n\n### 场景：使用规划 - 写作框架生成故事\n假设你正在运行类似 **Plan And Write** 类别的项目（如 *Learning to Reason for Long-Form Story Generation*），通常包含以下步骤：\n\n1.  **准备输入提示词**（Prompt）：\n    创建一个 `input.json` 或直接通过命令行传入故事主题。\n\n2.  **运行生成脚本**：\n    ```bash\n    python generate_story.py \\\n        --model_name_or_path \"meta-llama\u002FLlama-3-8b\" \\\n        --prompt \"Write a suspenseful story about a detective in Shanghai.\" \\\n        --max_length 2048 \\\n        --output_dir .\u002Fresults\n    ```\n\n3.  **查看结果**：\n    生成的故事通常保存在 `.\u002Fresults` 目录下，格式为 `.txt` 或 `.json`。\n\n### 场景：多智能体协作（Multi-Agent）\n对于 **Agents' Room** 或 **HAMLET** 等多智能体项目，通常需要启动多个角色实例：\n\n```bash\npython run_multi_agent.py \\\n    --config configs\u002Fdrama_script.yaml \\\n    --roles \"director,actor,critic\" \\\n    --topic \"A cyberpunk mystery\"\n```\n\n**关键提示**：\n*   请务必阅读所选具体论文仓库中的 `README.md`，因为参数（如 `--model_name`, `--temperature`）因模型架构而异。\n*   显存需求：生成长篇故事或多模态内容通常需要 24GB+ 显存（如 RTX 3090\u002F4090），小显存用户建议使用量化版本（如 `bitsandbytes`）或调用 API。","一位独立游戏开发者正试图利用大语言模型为其奇幻 RPG 游戏自动生成连贯且富有创意的长篇支线任务剧情。\n\n### 没有 Awesome-Story-Generation 时\n- **文献检索如大海捞针**：在 arXiv 和各类会议中手动筛选关于“故事生成”的论文，难以区分哪些是过时的前大模型时代研究，哪些是真正基于 LLM 的最新成果。\n- **缺乏系统性方法论**：面对长文本生成中常见的逻辑断裂和人设崩塌问题，找不到针对\"Plan And Write（规划与写作）”或“多智能体协作”的具体技术路径，只能盲目调整提示词。\n- **评估标准模糊**：不清楚如何量化评估生成故事的质量，缺乏权威的评估指标和数据集参考，导致迭代优化全靠主观感觉。\n- **错失前沿控制技巧**：不知道如何实现更精细的故事控制（如特定风格迁移或情节约束），生成的内容往往千篇一律，无法满足游戏设计的个性化需求。\n\n### 使用 Awesome-Story-Generation 后\n- **精准锁定前沿资源**：直接获取按时间排序的专属 LLM 时代论文列表，迅速定位到如\"Dynamic Hierarchical Outlining\"等解决长文逻辑的最新技术，节省数周调研时间。\n- **引入成熟架构方案**：参考\"Multi Agent\"和\"Better Storytelling\"分类下的论文，快速搭建起包含“规划者 - 撰写者 - 批评者”的多智能体工作流，显著提升剧情连贯性。\n- **建立科学评估体系**：利用\"Evaluation\"板块提供的最新综述和指标，建立起客观的故事质量打分机制，让剧情优化过程有据可依。\n- **实现高度可控创作**：借鉴\"More Controllable\"领域的研究成果，成功让 AI 根据预设的游戏世界观和角色弧光生成定制化剧情，大幅提升了玩家的沉浸感。\n\nAwesome-Story-Generation 将分散的学术智慧转化为可落地的工程指南，帮助开发者从“盲目试错”跃迁至“站在巨人肩膀上创新”。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyingpengma_Awesome-Story-Generation_a5a49028.png","yingpengma","Yingpeng MA","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fyingpengma_b4ca566e.png","Imagination will take you everywhere.","NLP2CT Lab","Macau SAR, China",null,"mayingpeng","yingpengma.github.io","https:\u002F\u002Fgithub.com\u002Fyingpengma",[86],{"name":87,"color":88,"percentage":89},"Python","#3572A5",100,601,29,"2026-04-03T20:15:53",1,"","未说明",{"notes":97,"python":95,"dependencies":98},"该仓库（Awesome-Story-Generation）是一个论文和资源列表，而非具体的可执行代码工具或模型框架。它主要收集了关于大语言模型（LLM）时代故事生成的研究论文、数据集和相关资源链接。因此，README 中未包含任何操作系统、GPU、内存、Python 版本或依赖库的安装需求。用户若需运行列表中提到的具体论文代码（如 HAMLET, MoPS 等），需前往各论文对应的独立代码仓库查看具体的环境配置要求。",[],[15],[101,102,103,104,105,106,107,108,109,110],"nlp","story-generation","language-generation","large-language-model","natural-language-processing","storytelling","open-ended","story","novel","narrative",4,"2026-03-27T02:49:30.150509","2026-04-06T05:44:07.720571",[],[]]