# PaperBanana: Automating Academic Illustration for AI Scientists

arXiv: https://arxiv.org/abs/2601.23265 · HTML: https://mlsanity.com/paper/2601.23265/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 74 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 30 of 34)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation](https://mlsanity.com/paper/2406.09961/) (2024)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization](https://mlsanity.com/paper/2402.11453/) (2024)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [LLM4SR: A Survey on Large Language Models for Scientific Research](https://mlsanity.com/paper/2501.04306/) (2025)
- [LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models](https://mlsanity.com/paper/2303.02927/) (2023)
- [AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ](https://mlsanity.com/paper/2310.00367/) (2023)
- [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023)
- [Kling-Omni Technical Report](https://mlsanity.com/paper/2512.16776/) (2025)
- [Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers](https://mlsanity.com/paper/2505.21497/) (2025)
- [Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks](https://mlsanity.com/paper/1804.03126/) (2018)
- [TikZero: Zero-Shot Text-Guided Graphics Program Synthesis](https://mlsanity.com/paper/2503.11509/) (2025)
- [Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code](https://mlsanity.com/paper/2412.02764/) (2024)
- [PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback](https://mlsanity.com/paper/2502.00988/) (2025)
- [Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets](https://mlsanity.com/paper/2512.15110/) (2025)
- [SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model](https://mlsanity.com/paper/2505.22126/) (2025)
- [FigGen: Text to Scientific Figure Generation](https://mlsanity.com/paper/2306.00800/) (2023)
- [IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation](https://mlsanity.com/paper/2601.04498/) (2026)
- [CoDA: Agentic Systems for Collaborative Data Visualization](https://mlsanity.com/paper/2510.03194/) (2025)
- [Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualization](https://mlsanity.com/paper/2402.07909/) (2024)
- [ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?](https://mlsanity.com/paper/2412.02368/) (2024)
- [DiagramEval: Evaluating LLM-Generated Diagrams via Graphs](https://mlsanity.com/paper/2510.25761/) (2025)
- [SciFig: Towards Automating Editable Figure Generation for Scientific Papers](https://mlsanity.com/paper/2601.04390/) (2026)

## Built on by (most cited first, 26 of 26)

- [GEMS: Agent-Native Multimodal Generation with Memory and Skills](https://mlsanity.com/paper/2603.28088/) (2026)
- [PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing](https://mlsanity.com/paper/2604.05018/) (2026)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs](https://mlsanity.com/paper/2605.30611/) (2026)
- [AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2602.24134/) (2026)
- [Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration](https://mlsanity.com/paper/2603.29590/) (2026)
- [AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation](https://mlsanity.com/paper/2603.28068/) (2026)
- [SciFigDetect: A Benchmark for AI-Generated Scientific Figure Detection](https://mlsanity.com/paper/2604.08211/) (2026)
- [SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation](https://mlsanity.com/paper/2606.30124/) (2026)
- [One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution](https://mlsanity.com/paper/2606.31478/) (2026)
- [SciForma: Structure-Faithful Generation of Scientific Diagrams](https://mlsanity.com/paper/2607.18091/) (2026)
- [GVR-Coder: A Visual-Feedback Framework for Structured SVG Generation in Complex Document and Meeting Scenarios](https://mlsanity.com/paper/2607.28073/) (2026)
- [DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable](https://mlsanity.com/paper/2608.00548/) (2026)
- [EdiTikZ: Scientific Figure Editing from Revision Trajectories](https://mlsanity.com/paper/2609.01409/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation](https://mlsanity.com/paper/2605.27931/) (2026)
- [Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models](https://mlsanity.com/paper/2606.05949/) (2026)
- [Imperfect Visual Verification for Code Edition : A Case Study on TikZ](https://mlsanity.com/paper/2606.15693/) (2026)
- [Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising](https://mlsanity.com/paper/2607.00407/) (2026)
- [SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence](https://mlsanity.com/paper/2607.27066/) (2026)
- [SuTRA : Structurally-Unified Tokenization with Root Awareness](https://mlsanity.com/paper/2608.18087/) (2026)
- [PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback](https://mlsanity.com/paper/2608.30241/) (2026)
- [ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication](https://mlsanity.com/paper/2609.16014/) (2026)
- [One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline](https://mlsanity.com/paper/2610.06852/) (2026)
- [How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices](https://mlsanity.com/paper/2610.11877/) (2026)
- [Stride: Scale-Aware Multi-Agent Evolutionary Refinement for Infographic Generation](https://mlsanity.com/paper/2610.13502/) (2026)

## Abstract (arXiv)

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.