论文/arXiv 2510.05188·22 天前

Plug-and-Play Dramaturge：通过协作式 LLM Agents 进行迭代叙事剧本润色的分而治之方法

针对长篇叙事剧本单次生成质量不足，Dramaturge 以分层多 LLM Agents 迭代审阅与协同修订，并在综合实验中验证效果。

AI 整理

• 具身模型

原文链接：Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents（arXiv 2510.05188 · 发布日期：2026-10-06）

Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents

针对长篇叙事剧本单次生成质量不足，Dramaturge 以分层多 LLM Agents 迭代审阅与协同修订，并在综合实验中验证效果。

核心要点

• 长篇剧本修订需同时把握全局结构与局部细节，直接由 LLM 修改易造成局部编辑与整体要求不一致。
• Dramaturge 采用面向任务与特征的分而治之流程，包含全局审阅、场景级审阅和分层协同修订。
• 自上而下的任务流让高层策略指导局部修改，并通过由粗到细的多轮迭代持续改进剧本。
• 综合实验显示其在剧本级整体质量和场景级细节上显著优于所有基线，且可即插即用整合到现有方法。

验证范围与局限：验证范围为长篇叙事剧本的剧本级整体质量与场景级细节。

英文摘要 (Abstract)

Although LLMs have been widely adopted for creative content generation, a single-pass process often struggles to produce high-quality long narratives. How to effectively revise and improve long narrative scripts like scriptwriters remains a significant challenge, as it demands a comprehensive understanding of the entire context to identify global structural issues and local detailed flaws, as well as coordinating revisions at multiple granularities and locations. Direct modifications by LLMs typically introduce inconsistencies between local edits and the overall narrative requirements. To address these issues, we propose Dramaturge, a task and feature oriented divide-and-conquer approach powered by hierarchical multiple LLM agents. It consists of a Global Review stage to grasp the overall storyline and structural issues, a Scene-level Review stage to pinpoint detailed scene and sentence flaws, and a Hierarchical Coordinated Revision stage that coordinates and integrates structural and detailed improvements throughout the script. The top-down task flow ensures that high-level strategies guide local modifications, maintaining contextual consistency. The review and revision workflow follows a coarse-to-fine iterative process, continuing through multiple rounds until no further substantive improvements can be made. Comprehensive experiments show that Dramaturge significantly outperforms all baselines in terms of script-level overall quality and scene-level details. Our approach is plug-and-play and can be easily integrated into existing methods to improve the generated scripts.

作者：Wenda Xie, Chao Guo, Yanqing Jing, Junle Wang, Yisheng Lv, Fei–Yue Wang

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2510.05188：Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents访问 2026-10-21