Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

The paper introduces SLIDEFORGE, an agentic framework that builds a Deck State Graph linking visual decomposition, native pptx object structure, and perceptual organization to enable controllable slide editing with preserved theme, layout, and native editability, alongside a new evaluation paradigm.

SourcearXiv Computer VisionAuthor: Haozhen Zheng, Fulin Wang, Tianhu Xiong, Yingjie Yu, Shengyi Qian, Hanchao Yu, Alex Schwing, Klara Nahrstedt, Mingyuan Wu
SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Sep 2026]

Title:SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts

View a PDF of the paper titled SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts, by Haozhen Zheng and 8 other authors

View PDF HTML (experimental)

Abstract: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.

Comments: EMNLP 2026 Main Conference. Haozhen and Fulin contributed equally

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2609.03109 [cs.CV]

(or arXiv:2609.03109v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.03109

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Haozhen Zheng [view email] [v1] Wed, 2 Sep 2026 19:44:31 UTC (26,284 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts, by Haozhen Zheng and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • SLIDEFORGE builds a Deck State Graph as an executable slide state linking visual decomposition, pptx object structure, and perceptual organization
  • It supports theme-preserving reconstruction via slide-native operations and rendered-state verification
  • Introduces an evaluation paradigm jointly measuring component recovery, preservation, restyling consistency, visual quality, and native editability
  • Outperforms direct prompting, screenshot-based agents, and generic code-agent baselines

Highlights and analysis are generated automatically and may contain errors. Check the original source.