Crafter: Multi-Agent Harness for Editable Scientific Figure Generation Scores +16pt Over Baselines (103 HF Upvotes)
Tsinghua University
Crafter (arXiv 2605.30611) presents a multi-agent system for generating editable scientific figures from diverse inputs (text, masks, sketches, key elements), coordinating five specialized agents around an evolving figure specification. The system uses diversity-driven plan exploration, structured corrective layers, and a verify-then-refine loop, outperforming the best baseline by 16.61 points on PaperBanana-Bench and 22.20 points on CraftBench across 279 samples. The companion CraftEditor converts raster outputs to editable SVGs.
Why it matters
Automates one of the most time-consuming parts of academic paper production; the CraftBench benchmark provides the first standardized evaluation for cross-type, cross-condition scientific figure generation. Top paper on HuggingFace Daily Papers for June 2 with 103 upvotes.
Importance: 3/5
103 HF upvotes (top paper on June 2); substantial benchmark improvements over prior baselines.