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.
@article{arxiv.2604.11969,
title = {Narrative-Driven Paper-to-Slide Generation via ArcDeck},
author = {Tarik Can Ozden and Sachidanand VS and Furkan Horoz and Ozgur Kara and Junho Kim and James Matthew Rehg},
journal= {arXiv preprint arXiv:2604.11969},
year = {2026}
}