arXiv Open Access 2026

Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration

Zhuoling Li Jiarui Zhang Ping Hu Jason Kuen Jiuxiang Gu +2 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (7)

Z

Zhuoling Li

J

Jiarui Zhang

P

Ping Hu

J

Jason Kuen

J

Jiuxiang Gu

H

Hossein Rahmani

J

Jun Liu

Format Sitasi

Li, Z., Zhang, J., Hu, P., Kuen, J., Gu, J., Rahmani, H. et al. (2026). Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration. https://arxiv.org/abs/2603.29590

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓