发表机构
Pocket FM; Princeton University; University of Michigan; University of Maryland; Universitat Pompeu Fabra（Pocket FM; 普林斯顿大学; 密歇根大学; 马里兰大学; 庞培法布拉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MAGNET多智能体叙事引擎和ATLAS幻觉检测管线，通过角色代理和世界状态追踪，在100页故事中减少41%注释和50%幻觉，实现连贯长篇小说生成。
AI 中文摘要
尽管大型语言模型（LLM）在创意小说生成方面表现出色，但在长篇小说中难以保持叙事一致性和连贯的情节线。在这项工作中，我们引入了一个统一的长篇叙事生成与验证框架。MAGNET是一个多智能体目标驱动的叙事引擎，用于生成故事，它使用基于角色的角色代理，根据共享的世界状态和不断演变的故事目标提出动作；而ATLAS是一个基于图的管线，用于比较生成故事中场景级的世界表示以检测幻觉。通过使用LLM编辑器、成对评分标准和ATLAS评估MAGNET，我们表明，与单模型提示和IBSEN相比，我们的框架产生了连贯的叙事。在100页时，与单模型基线相比，MAGNET分别减少了41%和50%的注释和幻觉；与IBSEN相比，分别减少了34%和45%，成对评分评估显示了类似的结果。这些结果表明，长篇叙事可以从显式的世界状态追踪和目标驱动的多智能体生成中涌现，为可控且结构连贯的长篇叙事生成提供了基础。
英文摘要
Although large language models (LLMs) have demonstrated impressive creative fiction generation, they struggle to maintain narrative consistency and coherent plot lines in long-form stories. In this work, we introduce MAGNET, a multi-agent goal-driven narrative engine for storytelling, which generates stories with persona-grounded character agents that propose actions based on a shared structured state and evolving story goals. We evaluate MAGNET on 20 and 100 page stories using LLM based editor annotations and rubric scoring. At both narrative lengths, MAGNET significantly reduces editor annotations and improves rubric scores compared to single-model prompting, StoryBox, and StoryWriter (p<0.05). Ablation experiments also show that the critic module, structured state, and goal sequencing each contribute significantly to performance (p<0.05). These results suggest that long-form narratives can emerge from explicit structured states, critic-based action refinement, and goal-driven multi-agent generation with loosely specified character personas, providing a foundation for controllable and structurally coherent long-form narrative generation.
