Saturday, February 14, 2026

Google AI Introduces PaperBanana: An Agentic Framework that Automates Academic illustrations

Good news! However, they only tested it on a single machine learning & AI conference, i.e. NIPS (Do not use NeurIPS abbreviation)!

Plotting and diagramming made easy!

"PaperBanana is an agentic framework designed to rescue researchers from the manual grind of creating publication-ready academic illustrations. By orchestrating a team of five specialized agents—Retriever, Planner, Stylist, Visualizer, and Critic—it transforms technical descriptions into high-fidelity methodology diagrams and numerically precise statistical plots. The system employs a dual-mode visualization strategy, utilizing image generation for diagrams and executable Matplotlib code for data plots to eliminate "visual hallucinations". Evaluated on the new PaperBananaBench dataset featuring 292 test cases from NeurIPS 2025, the framework outperformed standard baselines with a 17.0% gain in overall quality across faithfulness, conciseness, readability, and aesthetics. Essentially, it provides a professional "NeurIPS look" for AI scientists, ensuring that complex discoveries are as visually impressive as they are technically sound ..."

From the 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."

Google AI Introduces PaperBanana | ByteDance Releases Protenix-v1





No comments: