FigAgent: Towards Automatic Method Illustration Figure Generation for AI Scientific Papers

2026-02-06

AI Summary

This work addresses the inefficiency and heavy reliance on manual effort in generating method illustrations (MIs) for scientific papers. To overcome this limitation, we propose FigAgent—a multi-agent framework that, for the first time, abstracts human drawing expertise into reusable, evolvable, and composable illustration middleware. Inspired by human-like trial-and-error behavior, FigAgent employs an “explore-and-select” strategy to autonomously produce high-quality, structurally complex method illustrations. The framework integrates multi-agent collaboration, middleware evolution mechanisms, and experience distillation based on visually similar components. Experimental results demonstrate that FigAgent significantly enhances both the quality and automation level of method illustration generation compared to existing approaches.

Abstract

Method illustration figures (MIFs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. In this paper, we identify three key characteristics that substantially influence MIF generation quality, i.e., \emph{compositional complexity}, \emph{component similarity}, and \emph{design dynamics}. To handle these characteristics, we take inspiration from human authors'drawing practices and propose \textbf{FigAgent}, a novel multi-agent framework for automatically generating high-quality MIFs. Through multi-agent collaboration, our FigAgent distills drawing experiences across similar components of MIFs and encapsulates them into reusable tools that can be invoked during MIF generation, while evolving these tools to adapt to dynamic design requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIFs with complex structures. Extensive experiments show the efficacy of our method. Project is available \href{https://zhuolingli.github.io/FigAgent-page-project/}{here}.

Problem

• Method Illustrations
• Scientific Papers
• Automatic Generation
• Drawing Middleware
• Visual Communication

Innovation

• drawing middleware
• multi-agent framework
• method illustration generation
• Explore-and-Select strategy
• automatic scientific visualization