Metraipolis › archive › dc_28eeaf392b2a
SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation — arXiv:2608.03298
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03298
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:15:43.495Z
- SHA-256 of the archived text
142e2657e56992367d2756d8c2e3ed447900c9ba48464a1f597c9355301445ad- Stable URL of this page
https://metraipolis.com/documento/dc_28eeaf392b2a
How to cite
SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation — arXiv:2608.03298 — arXiv (en), https://arxiv.org/abs/2608.03298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28eeaf392b2a (Metraipolis archive dc_28eeaf392b2a, sha256 142e2657e56992367d2756d8c2e3ed447900c9ba48464a1f597c9355301445ad)
BibTeX
@misc{dc28eeaf392b2a,
title = {SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation — arXiv:2608.03298},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03298},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28eeaf392b2a; sha256 142e2657e56992367d2756d8c2e3ed447900c9ba48464a1f597c9355301445ad},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic presentation generation must preserve source content, maintain coherent visual design, render specialized objects, and produce usable artifacts. Existing systems meet only part of this requirement: templates preserve regularity but restrict adaptation, whereas free-form HTML or SVG gives models flexibility at the cost of low-level rendering decisions. This mismatch makes long technical decks brittle, especially when slides contain formulas, code, or data graphics. We present SeaSlides, an agentic slide-generation framework built around a semantic abstraction layer. Rather than authoring coordinates, inline styles, or raw SVG geometry, the model writes structured slide content through reusable components and capability modules, while templates own layout, style, and rendering. We instantiate this principle separately in HTML and Typst: SeaSlides-HTML uses template-defined DOM components, whereas SeaSlides-Typst uses template functions and package-backed modules. Capability modules route equations, code, and charts to dedicated renderers, and three feedback stages localize build errors, project-constraint violations, and visual defects before export. The two systems retain backend-specific syntax and contracts while sharing the same authoring boundary. For evaluation, we combine the 128-task UltraPresent validation setting with SeaSlidesBench-Rich, a new 32-task benchmark stressing mathematics, code, pseudocode, tables, charts, and diagrams. Across four generation models, both SeaSlides backends produce more readable, content-oriented source than SVG-heavy generation. A SeaSlides backend attains the highest rich-content macro-average under three of the four models while maintaining competitive overall qualitative performance. These results support semantic abstraction as a practical authoring principle across presentation backends. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.03298 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T12:05:52.777Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).