Narrative-Driven Paper-to-Slide Generation via ArcDeck
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 b...
| Authors | Tarik Can Ozden, Sachidanand VS, Furkan Horoz et al. |
|---|---|
| Primary category | cs.AI |
| Published | 13 April 2026 |
| Last updated at source | 13 April 2026 |
Models and datasets referencing this paper
- ArcDeck/ArcBenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.