High-fidelity diagram creation requires the complex orchestration of semantic topology, visual styling, and spatial layout, posing a significant challenge for automated systems. Existing methods also suffer from a representation gap: pixel-based models often lack precise control, while code-based synthesis limits intuitive flexibility. To bridge this gap, we introduce EvoDiagram, an agentic framework that generates object-level editable diagrams via an intermediate canvas schema. EvoDiagram employs a coordinated multi-agent system to decouple semantic intent from rendering logic, resolving conflicts across heterogeneous design layers. Additionally, we propose a design knowledge evolution mechanism that distills execution traces into a hierarchical memory of domain guidelines, enabling agents to retrieve context-aware expertise adaptively. We further release CanvasBench, a benchmark consisting of both data and metrics for canvas-based diagramming. Extensive experiments demonstrate that EvoDiagram exhibits excellent performance and balance against baselines in generating editable, structurally consistent, and aesthetically coherent diagrams. Our code is available at https://github.com/AuraX-AI/EvoDiagram.
@article{arxiv.2604.09568,
title = {EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution},
author = {Tianfu Wang and Leilei Ding and Ziyang Tao and Yi Zhan and Zhiyuan Ma and Wei Wu and Yuxuan Lei and Yuan Feng and Junyang Wang and Yin Wu and Yizhao Xu and Hongyuan Zhu and Qi Liu and Nicholas Jing Yuan and Yanyong Zhang and Hui Xiong},
journal= {arXiv preprint arXiv:2604.09568},
year = {2026}
}