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

Source: https://huggingface.co/papers/2605.30611

Abstract

Automated systems for generating scientific figures face limitations in handling diverse figure types and conditions, prompting the development of multi-agent frameworks that generalize across different input scenarios and produce editable output formats.

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; theirraster outputsfurther 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, amulti-agent harnessforfigure generationthat generalizes across figure types and input conditions without architectural changes, and CraftEditor, which applies the same pattern to convertraster outputsintoeditable SVGs. Moreover, we introduceCraftBench, 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 onPaperBanana-BenchandCraftBench, with ablations confirming each component’s independent contribution; CraftEditor faithfully converts outputs intoeditable SVGsthat surpass all baselines. Our code and benchmark are available at https://github.com/HaozheZhao/Crafter.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2605\.30611

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.30611 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.30611 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.30611 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.