Narrative-Driven Paper-to-Slide Generation via ArcDeck
For researchers and presenters, ArcDeck addresses the bottleneck of generating coherent, logically structured slides from academic papers.
ArcDeck improves paper-to-slide generation by explicitly modeling the source paper's logical flow through discourse trees and multi-agent refinement, outperforming existing methods in narrative coherence.
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.