PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs

TL;DR

PosterGen is a multi-agent LLM-based framework that automates the creation of conference posters by integrating content extraction, layout, styling, and rendering, resulting in visually appealing and semantically accurate posters.

Contribution

This work introduces PosterGen, a novel multi-agent system that mimics professional poster design workflows, improving aesthetic quality and reducing manual effort in paper-to-poster generation.

Findings

PosterGen outperforms existing methods in visual design quality.

Generated posters achieve high content fidelity and aesthetic coherence.

The VLM-based rubric effectively evaluates poster design quality.

Abstract

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.