用多智能体自动生成论文方法图，模仿人类绘图习惯。
Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
- 构建可复用的绘图中间件，支持动态演化和组合。
- 提出试错式策略，逐步生成复杂结构的方法图。
- 适合需要高效产出高质量插图的研究者使用。
方法图在科学论文中对传达核心思想至关重要，但其生成过程仍高度依赖人力。本文受人类作者绘图实践启发，提出一种名为 FigAgent 的新型多智能体框架，用于高质量自动方法图生成。该框架从相似组件的方法图中提炼绘图经验，并封装为可复用的绘图中间件，支持编排与动态演化以适应不断变化的绘图需求。此外，引入一种新颖的‘探索与选择’绘图策略，模拟人类试错过程，逐步构建具有复杂结构的方法图。大量实验证明了该方法的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。