APEX: Academic Poster Editing Agentic Expert

2026-01-08

arXiv.org

AI Summary

Existing approaches to academic poster generation are typically one-shot and non-interactive, making it difficult to support fine-grained user control over content density and layout aesthetics. To address this limitation, this work proposes APEX, the first interactive agent framework tailored for academic poster design. APEX enables precise alignment with user intent through multi-level API operations and a review-and-refine mechanism that supports granular editing. The study also introduces APEX-Bench, a new evaluation benchmark comprising 514 diverse instructions, along with a multidimensional vision-language model (VLM) evaluation protocol. Experimental results demonstrate that APEX significantly outperforms existing baselines in adhering to content instructions, controlling the scope of modifications, and preserving visual consistency.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Multiagent Systems: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Designing academic posters is a labor-intensive process requiring the precise balance of high-density content and sophisticated layout. While existing paper-to-poster generation methods automate initial drafting, they are typically single-pass and non-interactive, often fail to align with complex, subjective user intent. To bridge this gap, we propose APEX (Academic Poster Editing agentic eXpert), the first agentic framework for interactive academic poster editing, supporting fine-grained control with robust multi-level API-based editing and a review-and-adjustment Mechanism. In addition, we introduce APEX-Bench, the first systematic benchmark comprising 514 academic poster editing instructions, categorized by a multi-dimensional taxonomy including operation type, difficulty, and abstraction level, constructed via reference-guided and reference-free strategies to ensure realism and diversity. We further establish a multi-dimensional VLM-as-a-judge evaluation protocol to assess instruction fulfillment, modification scope, and visual consistency&harmony. Experimental results demonstrate that APEX significantly outperforms baseline methods. Our implementation is available at https://github.com/Breesiu/APEX.

Problem

• academic poster editing
• interactive editing
• user intent alignment
• fine-grained control
• non-interactive generation

Innovation

• agentic framework
• interactive editing
• academic poster generation
• multi-level API
• VLM-as-a-judge