Saved in:
Bibliographic Details
Main Authors: Shi, Chengxin, Cai, Qinnan, Chen, Zeyuan, Zeng, Long, Zhao, Yibo, Yu, Jing, Yu, Jianxiang, Li, Xiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.04794
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911360741277696
author Shi, Chengxin
Cai, Qinnan
Chen, Zeyuan
Zeng, Long
Zhao, Yibo
Yu, Jing
Yu, Jianxiang
Li, Xiang
author_facet Shi, Chengxin
Cai, Qinnan
Chen, Zeyuan
Zeng, Long
Zhao, Yibo
Yu, Jing
Yu, Jianxiang
Li, Xiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04794
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle APEX: Academic Poster Editing Agentic Expert
Shi, Chengxin
Cai, Qinnan
Chen, Zeyuan
Zeng, Long
Zhao, Yibo
Yu, Jing
Yu, Jianxiang
Li, Xiang
Artificial Intelligence
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.
title APEX: Academic Poster Editing Agentic Expert
topic Artificial Intelligence
url https://arxiv.org/abs/2601.04794