一句一剧：基于多智能体系统的个性化短剧生成

摘要

现有数字短剧制作方法通常依赖于一次性LLM生成的剧本与松散耦合的流水线，难以满足短剧生成的三个关键需求：(1) 叙事节奏——导致悬念设置薄弱、情节推进不足、结局缺乏吸引力；(2) 空间一致性——造成场景布局漂移、角色位置在不同片段间不一致；(3) 制作级质量控制——需要在剧本和视觉阶段进行大量人工审核与修正。我们提出“一句话，一部剧”（One Sentence, One Drama）——一种分层多智能体框架，通过结构化中间模块和迭代优化，将用户单句创意转化为完整制作的短剧。该方法基于三个核心组件：(1) 基于多智能体辩论的情节生成模块，确保短剧节奏与叙事连贯性；(2) 基于3D场景的首帧生成机制，建立共享空间参照系，保证不同片段间角色位置与场景布局的一致性；(3) 多阶段审核循环，在剧本、视觉和视频生成阶段进行全面错误检测与定向修正。我们还引入场景级背景音乐匹配与场景转换规划，以提升观众的沉浸式体验。为系统评估该任务，我们提出Short-Drama-Bench基准，该基准在标准视频质量指标基础上扩展了短剧专属评价标准。实验结果表明，我们的方法在叙事质量、跨片段一致性及整体观看体验上显著优于现有流水线。

English

Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements of short-drama generation: (1) narrative pacing, resulting in weak hooks, insufficient escalation, and unattractive endings; (2) spatial consistency, leading to drifting scene layouts and inconsistent character positions across clips; and (3) production-level quality control, requiring extensive manual review and correction across script and visual stages. We present One Sentence, One Drama, a hierarchical multi-agent framework that transforms a user's single-sentence idea into a fully produced short drama through structured intermediate modules and iterative refinement. Our approach is built upon three key components: (1) a multi-agent debate-based story generation module that enforces short-drama pacing and narrative coherence; (2) a 3D-grounded first-frame generation mechanism that establishes a shared spatial reference for consistent character positioning and scene layout across clips; and (3) multi-stage reviewer loops that perform comprehensive error detection and targeted revision across script, visual, and video generation stages. We also introduce scene-level BGM matching and scene transition planning to improve the audience's immersive experience. To systematically evaluate this task, we introduce Short-Drama-Bench, a benchmark that extends standard video quality metrics with short-drama-specific criteria. Experimental results demonstrate that our method significantly outperforms existing pipelines in narrative quality, cross-clip consistency, and overall viewing experience.