用叙事结构生成学术幻灯片，逻辑更连贯。
Narrative-Driven Paper-to-Slide Generation via ArcDeck
- 将论文转幻灯片视为叙事重构，构建论述树与全局承诺文档。
- 多智能体协作提升幻灯片逻辑性，生成结果叙事流畅度显著提高。
- 适合科研人员快速制作高质量学术汇报幻灯片。
我们提出ArcDeck，一种多智能体框架，将论文转幻灯片任务建模为结构化叙事重构。不同于直接摘要文本生成幻灯片的方法，ArcDeck显式建模源论文的逻辑流。首先解析输入，构建论述树并建立全局承诺文档，确保高层意图被保留。这些结构先验引导迭代式多智能体精炼过程，专用智能体反复批判与修订演示稿大纲，最终生成可视化布局与设计。为评估该方法，我们还引入ArcBench，一个新构建的学术论文-幻灯片配对基准数据集。实验结果表明，显式论述建模结合角色特异的智能体协同，显著提升了生成演示稿的叙事流与逻辑连贯性。
原文摘要 · Abstract (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.
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。