ArcDeck:叙事驱动的论文转幻灯片生成框架
阅读原文· arxiv.org研究团队提出 ArcDeck 多智能体框架,将论文转幻灯片任务重新定义为结构化叙事重建问题。与直接总结原文的现有方法不同,ArcDeck 通过解析输入构建话语树和全局承诺文档来显式建模论文逻辑流,并指导多智能体迭代优化演示大纲,最终渲染视觉布局。团队同时发布 ArcBench 基准测试集。实验表明,显式话语建模与角色特定智能体协调能显著提升生成演示的叙事流畅度和逻辑连贯性。
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.