CreAgentive：一个由智能体工作流驱动的多类别创意生成引擎
CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine
AI总结：
本文提出 CreAgentive，通过基于知识图谱的 Story Prototype 与三阶段多智能体工作流，解决大模型创意写作中的体裁、长度、连贯性和结构限制。
摘要：
我们提出了 CreAgentive，这是一个由智能体工作流驱动的多类别创意生成引擎，旨在解决当代大语言模型在撰写故事、戏剧及其他类别创意作品时的四个关键局限：体裁多样性受限、输出长度不足、叙事连贯性较弱，以及无法强制执行复杂的结构性构造。CreAgentive 的核心采用 Story Prototype（故事原型），这是一种与体裁无关、基于知识图谱的叙事表示，通过将人物、事件和环境编码为语义三元组，把故事逻辑与风格实现解耦。CreAgentive 采用包含三个阶段的智能体工作流：初始化阶段构建用户指定的叙事骨架；生成阶段由长期和短期目标引导多智能体对话，以实例化 Story Prototype；写作阶段利用该原型生成包含倒叙、伏笔等高级结构的多体裁文本。该架构降低了存储冗余，并克服了长篇生成的典型瓶颈。在大量实验中，CreAgentive 使用通用骨干模型以稳定质量和低成本（每100章低于1美元）生成了数千个章节。为评估性能，我们定义了一个包含10项叙事指标的二维框架，同时衡量质量与长度。结果表明，CreAgentive 持续优于强基线，并在多种体裁上取得稳健表现，质量接近人类创作的小说。
英文摘要：
We present CreAgentive, an agent workflow driven multi-category creative generation engine that addresses four key limitations of contemporary large language models in writing stories, drama and other categories of creatives: restricted genre diversity, insufficient output length, weak narrative coherence, and inability to enforce complex structural constructs. At its core, CreAgentive employs a Story Prototype, which is a genre-agnostic, knowledge graph-based narrative representation that decouples story logic from stylistic realization by encoding characters, events, and environments as semantic triples. CreAgentive engages a three-stage agent workflow that comprises: an Initialization Stage that constructs a user-specified narrative skeleton; a Generation Stage in which long- and short-term objectives guide multi-agent dialogues to instantiate the Story Prototype; a Writing Stage that leverages this prototype to produce multi-genre text with advanced structures such as retrospection and foreshadowing. This architecture reduces storage redundancy and overcomes the typical bottlenecks of long-form generation. In extensive experiments, CreAgentive generates thousands of chapters with stable quality and low cost (less than $1 per 100 chapters) using a general-purpose backbone model. To evaluate performance, we define a two-dimensional framework with 10 narrative indicators measuring both quality and length. Results show that CreAgentive consistently outperforms strong baselines and achieves robust performance across diverse genres, approaching the quality of human-authored novels.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
