Paper2Figure：面向学术论文图表生成的多智能体协作系统
Paper2Figure: A Multi-Agent Collaborative System for Figure Generation Towards Academic Research Paper
把「图」表示为可编辑的中间脚本语言（FigScript），再由渲染器出图、由多智能体迭代修订——这套「脚本中间表示 + 渲染 + 反思式修订」的范式可直接迁移到视觉领域的示意图/流程图/架构图生成与可控编辑，也提示了用结构化中间表示替代像素级扩散生成来获得可编辑性的思路。
原文依据 Generation Agents convert text into our designed FigScript language, encoding figure semantics, styles and layout.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论为研究论文自动生成清晰、准确的图表仍具挑战性，因为这需要语义理解、精确结构与视觉美感。现有方法难以在保真度与质量之间取得平衡：基于大语言模型（LLM）的代码类方法（如 SVG、Mermaid）结构性强但不够灵活，而图像生成模型（如 GPT-Image-1、Nano Banana）生成的图表难以编辑且往往不准确。我们提出 Paper2Figure，一个带有交互式网页平台的双多智能体系统，用于从论文到图表的生成。生成智能体将文本转换为我们设计的 FigScript 语言，该语言编码图表的语义、样式与布局。网页系统将 FigScript 渲染为初始图像，随后精修智能体对其迭代分析以定位问题，并修改 FigScript 以改善逻辑性、对齐、美观度与文本准确性。关键在于，用户可通过直观的网页界面进一步精修结果，从而确保对最终输出的完全控制。为评估 Paper2Figure，我们提出了 Paper2Figure Bench，这是一个包含 100 张学术图表及其配对描述的基准。实验表明，在无人工调整的全自动生成设定下，Paper2Figure 相较最优基线将准确性提升 12%、美观度提升 13.5%、完整性提升 17.0%。通过将自动生成与交互式编辑相结合，Paper2Figure 弥合了 AI 辅助与研究者控制之间的差距，为高质量学术图表创作提供了实用方案。
英文原文摘要 1552 字符
Automatically generating clear and accurate figures for research papers remains challenging, as it requires semantic understanding, precise structure, and visual aesthetics. Existing approaches struggle to balance fidelity and quality: large language model (LLM) code-based methods (e.g., SVG, Mermaid) are structured but inflexible, while image-generation models (e.g., GPT-Image-1, Nano Banana) produce hard-to-edit and often inaccurate figures. We present Paper2Figure, a dual multi-agent system with an interactive web platform for paper-to-figure generation. Generation Agents convert text into our designed FigScript language, encoding figure semantics, styles and layout. The web system renders the FigScript into an initial image, which Refinement Agents iteratively analyze to locate issues and revise the FigScript for improved logic, alignment, aesthetics and text accuracy. Crucially, users can further refine results through an intuitive web interface, ensuring full control over the final output. To evaluate Paper2Figure, we introduce Paper2Figure Bench, a benchmark comprising 100 academic figures with paired descriptions. Experiments demonstrate that Paper2Figure markedly improves accuracy by 12%, beauty by 13.5%, and completeness by 17.0% over state-of-the-art baselines in fully automatic generation without human adjustment. By combining automated generation with interactive edit, Paper2Figure bridges the gap between AI assistance and researcher control, offering a practical solution for high-quality academic figure creation.