# Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

arXiv: https://arxiv.org/abs/2605.30611 · HTML: https://mlsanity.com/paper/2605.30611/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 21 of 21)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ](https://mlsanity.com/paper/2310.00367/) (2023)
- [SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents](https://mlsanity.com/paper/2305.13040/) (2023)
- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning](https://mlsanity.com/paper/2310.12128/) (2023)
- [PaperBanana: Automating Academic Illustration for AI Scientists](https://mlsanity.com/paper/2601.23265/) (2026)
- [AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations](https://mlsanity.com/paper/2602.03828/) (2026)
- [GATEAU: Selecting Influential Samples for Long Context Alignment](https://mlsanity.com/paper/2410.15633/) (2024)
- [SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model](https://mlsanity.com/paper/2505.22126/) (2025)
- [A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks](https://mlsanity.com/paper/2510.05608/) (2025)
- [From Context to Skills: Can Language Models Learn from Context Skillfully?](https://mlsanity.com/paper/2604.27660/) (2026)
- [Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned](https://mlsanity.com/paper/2603.05344/) (2026)
- [P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark](https://mlsanity.com/paper/2505.17104/) (2025)
- [IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation](https://mlsanity.com/paper/2601.04498/) (2026)
- [AutoFigure-Edit: Generating Editable Scientific Illustration](https://mlsanity.com/paper/2603.06674/) (2026)
- [Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Papers](https://mlsanity.com/paper/2511.18036/) (2025)
- [TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning](https://mlsanity.com/paper/2603.03072/) (2026)
- [SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing](https://mlsanity.com/paper/2602.09809/) (2026)
- [OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward](https://mlsanity.com/paper/2604.05514/) (2026)
- [CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancement](https://mlsanity.com/paper/2604.09691/) (2026)

## Built on by (most cited first, 9 of 9)

- [Figures as Programs: Recursive Generation of Editable Scientific Figures](https://mlsanity.com/paper/2609.01006/) (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)
- [PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides](https://mlsanity.com/paper/2609.29718/) (2026)
- [PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback](https://mlsanity.com/paper/2608.30241/) (2026)
- [VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics](https://mlsanity.com/paper/2609.13294/) (2026)
- [FigAct: Turning Scientific Figures into Active Canvases for Explanation](https://mlsanity.com/paper/2609.36190/) (2026)
- [One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline](https://mlsanity.com/paper/2610.06852/) (2026)

## Abstract (arXiv)

Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensive parts of paper preparation. Existing automated systems each target a single figure type under text-only input, leaving the diversity of types and conditions researchers actually use unaddressed; their raster outputs further cannot be locally revised. Because scientific figures are structured compositions of discrete semantic components, the localized errors generators produce on such layouts demand not a stronger backbone but a harness. We instantiate this harness in two complementary systems: Crafter, a multi-agent harness for figure generation that generalizes across figure types and input conditions without architectural changes, and CraftEditor, which applies the same pattern to convert raster outputs into editable SVGs. Moreover, we introduce CraftBench, a benchmark spanning three figure types and four input conditions with human quality annotation. Experiments show that Crafter substantially outperforms both standalone generators and the agentic baseline on PaperBanana-Bench and CraftBench, with ablations confirming each component's independent contribution; CraftEditor faithfully converts outputs into editable SVGs that surpass all baselines. Our code and benchmark are available at https://github.com/HaozheZhao/Crafter.