PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
Hao Zheng, Xinyan Guan, Hao Kong, Jia Zheng, Hongyu Lin, Yaojie Lu, Ben He, Xianpei Han, Le Sun
2025-01-08
Summary
This paper talks about PPTAgent, a new AI system that can automatically create high-quality presentations from documents, focusing not just on content but also on design and how well everything fits together.
What's the problem?
Current AI systems that make presentations mostly focus on getting the content right, but they often ignore how the presentation looks and how well it flows. This makes the presentations they create less useful in real-world situations.
What's the solution?
The researchers created PPTAgent, which works in two steps. First, it looks at example presentations to learn about good structure and content. Then, it uses this knowledge to create outlines and slides that are consistent and well-organized. They also made PPTEval, a tool to check how good the presentations are in three areas: content, design, and how well everything fits together.
Why it matters?
This matters because it could make creating presentations much easier and faster for everyone, from students to business professionals. Instead of spending hours making slides, people could use PPTAgent to quickly create high-quality presentations that look good and make sense. This could save a lot of time and help people communicate their ideas more effectively.
Abstract
Automatically generating presentations from documents is a challenging task that requires balancing content quality, visual design, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, often overlooking visual design and structural coherence, which limits their practical applicability. To address these limitations, we propose PPTAgent, which comprehensively improves presentation generation through a two-stage, edit-based approach inspired by human workflows. PPTAgent first analyzes reference presentations to understand their structural patterns and content schemas, then drafts outlines and generates slides through code actions to ensure consistency and alignment. To comprehensively evaluate the quality of generated presentations, we further introduce PPTEval, an evaluation framework that assesses presentations across three dimensions: Content, Design, and Coherence. Experiments show that PPTAgent significantly outperforms traditional automatic presentation generation methods across all three dimensions. The code and data are available at https://github.com/icip-cas/PPTAgent.