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

• URL: http://arxiv.org/abs/2605.30611v1
• Date: Thu, 28 May 2026 22:04:30 GMT
• Title: Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
• Abstract summary: We develop automated systems for producing publication-quality illustrations from scientific figures.<n>Crafter is a multi-agent harness figure generation that generalizes across figure types without architectural changes.<n>CraftEditor faithfully converts outputs into editable SVGs.
• Score: 62.54193387399707
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Figures as Programs: Recursive Generation of Editable Scientific Figures [79.78366479117878]
  Recent image-generation models can synthesize visually appealing figures, but producing a human-satisfactory result in a single generation step remains difficult.<n>We formulate textscFigTree, a textitmulti-agent system that automatically transforms scientific paper into a structured vector figure.<n>A render-critic refinement loop jointly inspects the rendered figure and its underlying program, enabling visual defects to be traced to specific statements and accurately repaired.
  arXiv  Detail & Related papers  (2026-09-01T09:53:47Z)
• GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers [2.593510481959727]
  We propose GenGA, a new generation framework that directly produces figures in vector format.<n>By generating figures as a collection of vector elements with a hierarchical structure, GenGA produces outputs that can be seamlessly imported into existing drawing tools.<n> Experimental results show that GenGA achieves superior editing simplicity compared to other methods, and even surpasses human-authored GAs in conciseness and semantic alignment.
  arXiv  Detail & Related papers  (2026-08-05T23:53:02Z)
• SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions [66.46898035008782]
  We present SciDiagramEdit, a benchmark and skill-evolution framework that learns from natural paper revisions.<n>An agentic proposer continually refines the agent's skill specification from execution traces over multiple epochs.<n>The resulting skill progressively lifts edit accuracy on a held-out validation set.
  arXiv  Detail & Related papers  (2026-07-16T17:58:36Z)
• Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework [82.66443886385125]
  Paper Circle is a discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature.<n>The system comprises two complementary pipelines: (1) a Discovery Pipeline that integrates offline and online retrieval from multiple sources, multi-agent scoring, diversity-aware ranking, and structured outputs; and (2) an Analysis Pipeline that transforms individual papers into structured knowledge graphs with typed nodes such as concepts, methods, and figures.
  arXiv  Detail & Related papers  (2026-04-07T17:59:58Z)
• StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation [57.06461272772509]
  StdGEN++ is a novel and comprehensive system for generating high-fidelity, semantically decomposed 3D characters from diverse inputs.<n>It achieves state-of-the-art performance, significantly outperforming existing methods in geometric accuracy and semantic disentanglement.<n>The resulting structural independence unlocks advanced downstream capabilities, including non-destructive editing, physics-compliant animation, and gaze tracking.
  arXiv  Detail & Related papers  (2026-01-12T15:41:27Z)
• From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration [38.72208780072352]
  VisPainter is a multi-agent framework for scientific illustration built upon the model context protocol.<n>It orchestrates three specialized modules-a Manager, a Designer, and a Toolbox-to collaboratively produce diagrams compatible with standard vector graphics software.<n>It assesses high-information-density scientific illustrations from four aspects: content, layout, visual perception, and interaction cost.
  arXiv  Detail & Related papers  (2025-10-31T13:00:49Z)
• Contrastive Learning and Mixture of Experts Enables Precise Vector Embeddings [0.0]
  This paper improves upon the vectors embeddings of scientific text by assembling niche datasets using co-citations as a similarity metric.<n>We apply a novel Mixture of Experts (MoE) extension pipeline to pretrained BERT models, where every multi-layer perceptron section is enlarged and copied into multiple distinct experts.
  arXiv  Detail & Related papers  (2024-01-28T17:34:42Z)
• Twist Decoding: Diverse Generators Guide Each Other [116.20780037268801]
  We introduce Twist decoding, a simple and general inference algorithm that generates text while benefiting from diverse models. Our method does not assume the vocabulary, tokenization or even generation order is shared.
  arXiv  Detail & Related papers  (2022-05-19T01:27:53Z)
• Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator [28.325133809296464]
  We propose a novel Component-Aware Module (CAM), which supervises the generator to decouple content and style at a more fine-grained level. Our approach outperforms state-of-the-art one-shot font generation methods. It can be applied to handwritten word synthesis and scene text image editing.
  arXiv  Detail & Related papers  (2022-04-30T03:41:49Z)
• Transformer for Graphs: An Overview from Architecture Perspective [86.3545861392215]
  It's imperative to sort out the existing Transformer models for graphs and systematically investigate their effectiveness on various graph tasks. We first disassemble the existing models and conclude three typical ways to incorporate the graph information into the vanilla Transformer. Our experiments confirm the benefits of current graph-specific modules on Transformer and reveal their advantages on different kinds of graph tasks.
  arXiv  Detail & Related papers  (2022-02-17T06:02:06Z)
• Rethinking Text Line Recognition Models [57.47147190119394]
  We consider two decoder families (Connectionist Temporal Classification and Transformer) and three encoder modules (Bidirectional LSTMs, Self-Attention, and GRCLs) We compare their accuracy and performance on widely used public datasets of scene and handwritten text. Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length.
  arXiv  Detail & Related papers  (2021-04-15T21:43:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.