Saved in:
Bibliographic Details
Main Authors: Li, Zhuoling, Zhang, Jiarui, Hu, Ping, Kuen, Jason, Gu, Jiuxiang, Rahmani, Hossein, Liu, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.29590
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912994556903424
author Li, Zhuoling
Zhang, Jiarui
Hu, Ping
Kuen, Jason
Gu, Jiuxiang
Rahmani, Hossein
Liu, Jun
author_facet Li, Zhuoling
Zhang, Jiarui
Hu, Ping
Kuen, Jason
Gu, Jiuxiang
Rahmani, Hossein
Liu, Jun
contents Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration from human authors' drawing practices and correspondingly propose \textbf{FigAgent}, a novel multi-agent framework for high-quality automatic MI generation. Our FigAgent distills drawing experiences from similar components across MIs and encapsulates them into reusable drawing middlewares that can be orchestrated for MI generation, while evolving these middlewares to adapt to dynamically evolving drawing requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures. Extensive experiments show the efficacy of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29590
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
Li, Zhuoling
Zhang, Jiarui
Hu, Ping
Kuen, Jason
Gu, Jiuxiang
Rahmani, Hossein
Liu, Jun
Graphics
Artificial Intelligence
Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration from human authors' drawing practices and correspondingly propose \textbf{FigAgent}, a novel multi-agent framework for high-quality automatic MI generation. Our FigAgent distills drawing experiences from similar components across MIs and encapsulates them into reusable drawing middlewares that can be orchestrated for MI generation, while evolving these middlewares to adapt to dynamically evolving drawing requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures. Extensive experiments show the efficacy of our method.
title Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
topic Graphics
Artificial Intelligence
url https://arxiv.org/abs/2603.29590