基于叙事驱动的ArcDeck：从论文到幻灯片的智能生成系统

摘要

我们推出ArcDeck——一个将论文转化为幻灯片的过程构建为结构化叙事重建任务的多智能体框架。与现有方法直接对原始文本进行摘要生成幻灯片不同，ArcDeck显式建模源论文的逻辑脉络。该框架首先解析输入内容以构建语篇树并生成全局主旨文档，确保高层次论述意图得以保留。这些结构化先验信息随后引导迭代式的多智能体优化流程：在渲染最终视觉布局与设计前，由特定功能智能体对演示文稿框架进行多轮批判性修订。为评估本方法，我们还构建了ArcBench基准数据集，该全新整理的学术论文-幻灯片配对基准包含丰富学科领域。实验结果表明，显式语篇建模与角色化智能体协作机制的有机结合，显著提升了生成演示文稿的叙事流畅度与逻辑连贯性。

English

We introduce ArcDeck, a multi-agent framework that formulates paper-to-slide generation as a structured narrative reconstruction task. Unlike existing methods that directly summarize raw text into slides, ArcDeck explicitly models the source paper's logical flow. It first parses the input to construct a discourse tree and establish a global commitment document, ensuring the high-level intent is preserved. These structural priors then guide an iterative multi-agent refinement process, where specialized agents iteratively critique and revise the presentation outline before rendering the final visual layouts and designs. To evaluate our approach, we also introduce ArcBench, a newly curated benchmark of academic paper-slide pairs. Experimental results demonstrate that explicit discourse modeling, combined with role-specific agent coordination, significantly improves the narrative flow and logical coherence of the generated presentations.

基于叙事驱动的ArcDeck：从论文到幻灯片的智能生成系统

Narrative-Driven Paper-to-Slide Generation via ArcDeck

摘要

Support