EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
Tianfu Wang, Leilei Ding, Ziyang Tao, Yi Zhan, Zhiyuan Ma, Wei Wu, Yuxuan Lei, Yuan Feng, Junyang Wang, Yin Wu, Yizhao Xu, Hongyuan Zhu, Qi Liu, Nicholas Jing Yuan, Yanyong Zhang, Hui Xiong

TL;DR
EvoDiagram is a novel agentic framework that creates editable diagrams by evolving design expertise and decoupling semantic intent from rendering, improving control and flexibility.
Contribution
It introduces a multi-agent system with a knowledge evolution mechanism for high-quality, editable diagram generation, bridging the gap between pixel-based and code-based methods.
Findings
EvoDiagram outperforms baselines in generating editable, consistent diagrams.
The framework effectively balances aesthetics and structural accuracy.
The release of CanvasBench provides a new benchmark for diagramming tasks.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
