mlsanityData to 14 Oct 2026

Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration

arXiv 2603.29590 ↗First posted 6 Feb 2026cs.GR cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration from human authors' drawing practices and correspondingly propose FigAgent, a novel multi-agent framework for high-quality automatic MI generation. Our FigAgent distills drawing experiences from similar components across MIs and encapsulates them into reusable drawing middlewares that can be orchestrated for MI generation, while evolving these middlewares to adapt to dynamically evolving drawing requirements. Besides, a novel Explore-and-Select drawing strategy is introduced to mimic the human-like trial-and-error manner for gradually constructing MIs with complex structures. Extensive experiments show the efficacy of our method.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 6 Feb 2026.

Builds on

31 of 42 references.

References · 31

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  5. 2023A Survey on Multimodal Large Language Modelscited by 909
  6. 2024Large Language Models: A Surveycited by 525
  7. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 159
  8. 2023StarVector: Generating Scalable Vector Graphics Code from Images and Textcited by 102
  9. 2023AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZcited by 79
  10. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 75
  11. 2025OmniSVG: A Unified Scalable Vector Graphics Generation Modelcited by 74
  12. 2024Empowering LLMs to Understand and Generate Complex Vector Graphicscited by 66
19 more
  1. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 55
  2. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Modelscited by 38
  3. 2024Text-to-Vector Generation with Neural Path Representationcited by 33
  4. 2022OCR-VQGAN: Taming Text-within-Image Generationcited by 31
  5. 2024From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editingcited by 31
  6. 2023DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planningcited by 29
  7. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 27
  8. 2026PaperBanana: Automating Academic Illustration for AI Scientistscited by 26
  9. 2025TikZero: Zero-Shot Text-Guided Graphics Program Synthesiscited by 24
  10. 2026AutoFigure: Generating and Refining Publication-Ready Scientific Illustrationscited by 23
  11. 2025Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasetscited by 20
  12. 2024SuperSVG: Superpixel-based Scalable Vector Graphics Synthesiscited by 19
  13. 2025SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Modelcited by 19
  14. 2024Layered Image Vectorization via Semantic Simplificationcited by 18
  15. 2023FigGen: Text to Scientific Figure Generationcited by 17
  16. 2025SVGen: Interpretable Vector Graphics Generation with Large Language Modelscited by 14
  17. 2025DiagramEval: Evaluating LLM-Generated Diagrams via Graphscited by 8
  18. 2025STRICT: Stress Test of Rendering Images Containing Textcited by 7
  19. 2025Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Paperscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Figures as Programs: Recursive Generation of Editable Scientific Figurescited by 2
  2. 2026Agentic Visual Generation: From Generative Models to Agentic Controlcited by 1
  3. 2026Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussionscited by 0
  4. 2026ToolFG: Towards Well-Grounded Fine-Grained Image Classificationcited by 0
  5. 2026Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agentscited by 0