PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation

TL;DR

PosterForest is a training-free framework that uses hierarchical reasoning and a structured Poster Tree to generate scientific posters with improved coherence, flow, and visual balance.

Contribution

It introduces the Poster Tree representation and hierarchical agents for recursive poster refinement, enabling effective poster generation without extra training.

Findings

PosterForest outperforms prior methods in automatic evaluations.

It achieves better semantic coherence and visual harmony.

The method requires no additional training or domain-specific supervision.

Abstract

Automating scientific poster generation requires hierarchical document understanding and coherent content-layout planning. Existing methods often rely on flat summarization or optimize content and layout separately. As a result, they often suffer from information loss, weak logical flow, and poor visual balance. We present PosterForest, a training-free framework for scientific poster generation. Our method introduces the Poster Tree, a structured intermediate representation that captures document hierarchy and visual-textual semantics across multiple levels. Building on this representation, content and layout agents perform hierarchical reasoning and recursive refinement, progressively optimizing the poster from global organization to local composition. This joint optimization improves semantic coherence, logical flow, and visual harmony. Experiments show that PosterForest outperforms prior methods in both automatic and human evaluations, without additional training or domain-specific supervision.