纸香蕉：为AI科学家自动化生成学术插图

PaperBanana: Automating Academic Illustration for AI Scientists

January 30, 2026

作者: Dawei Zhu, Rui Meng, Yale Song, Xiyu Wei, Sujian Li, Tomas Pfister, Jinsung Yoon

cs.AI

摘要

尽管基于语言模型的自主AI科学家发展迅猛，但生成可直接发表的学术插图仍是研究流程中劳动密集型的瓶颈环节。为减轻这一负担，我们推出PaperBanana——一个用于自动生成出版级学术插图的智能体框架。该框架依托前沿视觉语言模型与图像生成技术，通过协调专业化智能体实现参考文献检索、内容风格规划、图像渲染及基于自我批判的迭代优化。为系统评估框架性能，我们构建了包含292个测试案例的PaperBananaBench评估集，这些案例源自NeurIPS 2025会议论文的方法论图示，覆盖多研究领域与插图风格。综合实验表明，PaperBanana在忠实度、简洁性、可读性与美学品质上持续超越主流基线方法。我们进一步证明该方法可有效扩展至高质量统计图表的生成。总体而言，PaperBanana为出版级插图的自动化生成开辟了新路径。

English

Despite rapid advances in autonomous AI scientists powered by language models, generating publication-ready illustrations remains a labor-intensive bottleneck in the research workflow. To lift this burden, we introduce PaperBanana, an agentic framework for automated generation of publication-ready academic illustrations. Powered by state-of-the-art VLMs and image generation models, PaperBanana orchestrates specialized agents to retrieve references, plan content and style, render images, and iteratively refine via self-critique. To rigorously evaluate our framework, we introduce PaperBananaBench, comprising 292 test cases for methodology diagrams curated from NeurIPS 2025 publications, covering diverse research domains and illustration styles. Comprehensive experiments demonstrate that PaperBanana consistently outperforms leading baselines in faithfulness, conciseness, readability, and aesthetics. We further show that our method effectively extends to the generation of high-quality statistical plots. Collectively, PaperBanana paves the way for the automated generation of publication-ready illustrations.