PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs
This addresses a time-consuming task for researchers preparing conference posters, offering an automated solution with improved design quality.
The authors tackled the paper-to-poster generation problem by proposing PosterGen, a multi-agent LLM framework that mimics professional designers to create aesthetically pleasing posters. Experimental results show it matches content fidelity and significantly outperforms existing methods in visual design, producing presentation-ready posters with minimal human refinement.
Multi-agent systems built upon large language models (LLMs) have demonstrated remarkable capabilities in tackling complex compositional tasks. In this work, we apply this paradigm to the paper-to-poster generation problem, a practical yet time-consuming process faced by researchers preparing for conferences. While recent approaches have attempted to automate this task, most neglect core design and aesthetic principles, resulting in posters that require substantial manual refinement. To address these design limitations, we propose PosterGen, a multi-agent framework that mirrors the workflow of professional poster designers. It consists of four collaborative specialized agents: (1) Parser and Curator agents extract content from the paper and organize storyboard; (2) Layout agent maps the content into a coherent spatial layout; (3) Stylist agents apply visual design elements such as color and typography; and (4) Renderer composes the final poster. Together, these agents produce posters that are both semantically grounded and visually appealing. To evaluate design quality, we introduce a vision-language model (VLM)-based rubric that measures layout balance, readability, and aesthetic coherence. Experimental results show that PosterGen consistently matches in content fidelity, and significantly outperforms existing methods in visual designs, generating posters that are presentation-ready with minimal human refinements.