Narrative-Driven Paper-to-Slide Generation via ArcDeck
Tarik Can Ozden, Sachidanand VS, Furkan Horoz, Ozgur Kara, Junho Kim, James Matthew Rehg

TL;DR
ArcDeck is a multi-agent framework that improves paper-to-slide generation by explicitly modeling the paper's logical flow and narrative structure, leading to more coherent presentations.
Contribution
It introduces a novel discourse-aware multi-agent approach and a new benchmark, ArcBench, for structured paper-to-slide generation.
Findings
Explicit discourse modeling enhances narrative coherence.
Role-specific agent coordination improves slide quality.
ArcDeck outperforms existing methods on ArcBench.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
