PaperBanana: Automating Academic Illustration for AI Scientists
PaperBanana automates publication-ready academic illustrations via agentic VLM and image generation, outperforming baselines on a 292-case benchmark.
Published Jan 30, 20261 citation▲ 230 on Hugging FaceCode ★ 7,132arXiv ↗
Only vote on papers you've read. Sign in with GitHub to vote.
PaperBanana delivers impressive, benchmark-backed automated academic illustrations through smart retrieval and layout planning, though its self-critique loop and synthetic NeurIPS benchmark leave serious questions about real-world plot fidelity and true autonomy.
Abstract
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.