Metraipolis › archive › dc_a67d454a3685

SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts — arXiv:2609.03109

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03109
License (as archived)
CC0-1.0
Archived
2026-10-17T02:56:10.278Z
SHA-256 of the archived text
caaa5b689e00b93307028dcdd4c5dbe0542c2876f055bbcc26afc55203c9555e
Stable URL of this page
https://metraipolis.com/documento/dc_a67d454a3685

How to cite

SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts — arXiv:2609.03109 — arXiv (en), https://arxiv.org/abs/2609.03109 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a67d454a3685 (Metraipolis archive dc_a67d454a3685, sha256 caaa5b689e00b93307028dcdd4c5dbe0542c2876f055bbcc26afc55203c9555e)
BibTeX
@misc{dca67d454a3685,
  title = {SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts — arXiv:2609.03109},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03109},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a67d454a3685; sha256 caaa5b689e00b93307028dcdd4c5dbe0542c2876f055bbcc26afc55203c9555e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03109. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current AI agents compellingly describe slides. However, AI-assisted slide editing requires more than understanding: the output must retain layout, style, component structure, and native editability. Towards, AI-assisted slide editing, existing agents operate on screenshots or weak document representations and often fragment coherent visual units, rasterize editable content, or break layout. In contrast, for controllable slide editing, we introduce an agentic framework, SLIDEFORGE, which builds a Deck State Graph, an executable slide state that links visual decomposition, native pptx object structure, and perceptual organization. By recovering human-referable components while retaining fine-grained editable structure, SLIDEFORGE supports theme-preserving reconstruction through slide-native operations and rendered-state verification. We further introduce an evaluation paradigm for controllable slide transformation that jointly measures component recovery, preservation, restyling consistency, visual quality, and native editability. Experiments show that SLIDEFORGE outperforms direct prompting, screenshot-based agents, and generic code-agent baselines across these dimensions. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.03109 — 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 2026-10-17T02:27:18.935Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).