PPTAgent, a tool for utilizing LLMs to generate PowerPoint presentations from documents.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"iflow-mcp-icip-cas-pptagent","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides <p align="center"> 📄 <a href="https://arxiv.org/abs/2501.03936" target="_blank">Paper</a> | 🤗 <a href="#open-source-" target="_blank">OpenSource</a> | 📝 <a href="./DOC.md" target="_blank">Documentation</a> | <a href="https://deepwiki.com/icip-cas/PPTAgent" target="_blank"><img src="https://deepwiki.com/icon.png" alt="Ask DeepWiki"> DeepWiki</a> | 🙏 <a href="#citation-" target="_blank">Citation</a> </p> We present PPTAgent, an innovative system that automatically generates presentations from documents. Drawing inspiration from human presentation creation methods, our system employs a two-step process to ensure excellence in overall quality. Additionally, we introduce **PPTEval**, a comprehensive evaluation framework that assesses presentations across multiple dimensions. ## Open Source 🤗 We have released our model and data at [HuggingFace](https://huggingface.co/collections/ICIP/pptagent-68b80af43b4f4e0cb14d0bb2). ## Demo Video 🎥 https://github.com/user-attachments/assets/c3935a98-4d2b-4c46-9b36-e7c598d14863 ## Distinctive Features ✨ - **Dynamic Content Generation**: Creates slides with seamlessly integrated text and images - **Smart Reference Learning**: Leverages existing presentations without requiring manual annotation - **Comprehensive Quality Assessment**: Evaluates presentations through multiple quality metrics ## Case Study 💡 - #### [Iphone 16 Pro](https://www.apple.com/iphone-16-pro/) <div style="display: flex; flex-wrap: wrap; gap: 10px;"> <img src="../resource/iphone16pro/0001.jpg" alt="图片1" width="200"/> <img src="../resource/iphone16pro/0002.jpg" alt="图片2" width="200"/> <img src="../resource/iphone16pro/0003.jpg" alt="图片3" width="200"/> <img src="../resource/iphone16pro/0004.jpg" alt="图片4" width="200"/> <img src="../resource/iphone16pro/0005.jpg" alt="图片5" width="200"/> <img src=".…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.