发表机构
UC Santa Barbara; CUHK; National University of Singapore; University of New South Wales; Tongji University（加州大学圣巴巴拉分校; 香港中文大学; 新加坡国立大学; 新南威尔士大学; 同济大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出多智能体系统FigTree，将科学图形生成转化为递归SVG程序构建任务，可从论文生成高质量可编辑矢量图形，其编辑效果优于现有光栅方法。
AI 中文摘要
科学方法论图形对于清晰传达复杂方法至关重要，但创建这些图形仍需大量人力，通常需要多轮优化。近期的图像生成模型可合成视觉效果吸引人的光栅图形，但仅通过单步生成得到令人满意的结果仍很困难。此外，无论是人类还是模型，都难以对光栅图形进行精确编辑。我们将科学图形生成为递归SVG程序构建任务，并提出多智能体系统FigTree，该系统可自动将科学论文转换为结构化矢量图形。FigTree以源论文为图形内容基础，将图形分解为局部区域的层次结构，将每个区域生成为简短的SVG程序，并组装生成的片段。渲染-评判优化循环会联合检查渲染后的图形及其底层程序，使视觉缺陷可追溯至特定语句并进行准确修复。我们针对FigTree在图形质量和可编辑性方面开展了广泛评估，结果表明FigTree可生成高质量图形，且相比现有基于光栅的方法，其编辑效果更优。
英文摘要
Scientific methodology figures are essential for communicating complex methods clearly, yet creating them remains labor-intensive and typically requires multiple rounds of refinement. Recent image-generation models can synthesize visually appealing raster figures, but producing a human-satisfactory result in a single generation step remains difficult. Moreover, precise edits to raster figures are challenging for both humans and models. We formulate scientific figure generation as recursive SVG program construction and propose \textsc{FigTree}, a \textit{multi-agent} system that automatically transforms a scientific paper into a structured vector figure. \textsc{FigTree} grounds figure content in the source paper, decomposes a figure into a hierarchy of local regions, generates each region as a short SVG program, and assembles the resulting fragments. A render-critic refinement loop jointly inspects the rendered figure and its underlying program, enabling visual defects to be traced to specific statements and accurately repaired. We conduct extensive evaluations of \textsc{FigTree} on figure quality and editability, showing that \textsc{FigTree} produces high-quality figures, while also enabling more effective editing than existing raster-based methods.
