SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation

TL;DR

SlideGen is a modular, multimodal system that uses collaborative vision-language agents to generate high-quality, visually appealing scientific presentation slides from papers, surpassing existing methods in quality and faithfulness.

Contribution

We introduce SlideGen, a novel agent-based framework that integrates multimodal reasoning and visual planning for automated scientific slide generation.

Findings

Outperforms existing methods in visual quality and content faithfulness

Produces slides with logical flow and expert-level visual presentation

Establishes a new state-of-the-art in automated slide creation

Abstract

Generating academic slides from scientific papers is a challenging multimodal reasoning task that requires both long context understanding and deliberate visual planning. Existing approaches largely reduce it to text only summarization, overlooking the visual component and design intensive nature of slide creation. In this paper we introduce SlideGen, an agentic, modular, and visual in the loop framework for scientific paper to slide generation. SlideGen orchestrates a group of vision language agents that reason collaboratively over the document structure and semantics, producing editable PPTX slides with logical flow and compelling visual presentation. By integrating coordinated outlining, mapping, arrangement, note synthesis, and iterative refinement, our system consistently delivers slides of expert level quality. Across diverse benchmarks and strong baselines, SlideGen outperforms existing methods in visual quality, content faithfulness, and readability, positioning it as the new state of the art in automated slide generation. Our work establishes a foundation for design aware multimodal slide generation, demonstrating how agentic collaboration can bridge understanding and presentation in complex multimodal reasoning tasks.