用角色驱动的多智能体生成长篇故事，提升连贯性与一致性。
From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives
- 角色代理基于共享世界状态和目标提出行动，实现动态叙事。
- 100页故事中幻觉减少50%，标注量降低41%，优于单模型基线。
- 适合需要结构化长篇创作的AI编剧、游戏剧情设计者使用。
尽管大语言模型在创造性小说生成方面表现优异，但在长篇故事中仍难以维持情节连贯性。本文提出统一框架MAGNET，一种基于多智能体的目标驱动叙事引擎，通过人物属性驱动的角色代理，根据共享世界状态和不断演进的故事目标提出行动；同时引入ATLAS，一个基于图的流水线，用于对比生成故事中各场景的世界表征以检测幻觉。通过LLM编辑、成对评分规则及ATLAS评估，结果表明该框架在100页故事中相较单模型提示和IBSEN分别将标注量减少41%和34%，幻觉减少50%和45%，成对评分也显示类似优势。这表明显式世界状态追踪与目标驱动的多智能体生成可促成长篇叙事的自然涌现，为可控且结构清晰的长篇叙事生成提供基础。
原文摘要 · Abstract (English)
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 a unified framework for long-form narrative generation and verification. MAGNET, a multi-agent goal-driven narrative engine for storytelling, generates stories with persona-grounded character agents that propose actions based on a shared world state and evolving story goals, while ATLAS is a graph-based pipeline that compares scene-level world representations across a generated story to detect hallucinations. By evaluating MAGNET using an LLM editor, pairwise rubric scoring, and ATLAS, we show that our framework produces coherent narratives compared to single-model prompting and IBSEN. At 100 pages, MAGNET reduced annotations and hallucinations by 41 and 50%, respectively, compared to the single model baseline and by 34 and 45%, respectively, compared to IBSEN, with pairwise rubric evaluation showing similar results. These results suggest that long-form narratives can emerge from explicit world-state tracking and goal-driven multi-agent generation, providing a foundation for controllable and structurally coherent long-form narrative generation.
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。