arXiv cs.CL· Tianfu Wang, Leilei Ding, Ziyang Tao, Yi Zhan, Zhiyuan Ma, Wei Wu, Yuxuan Lei, Junyang Wang, Yizhao Xu, Yin WU, Zhengyu Hu, Hongyuan Zhu, Nicholas Jing Yuan, Yanyong Zhang, Hui Xiong·· 11 小时前AI 评分34
EvoDesign：通过设计经验进化实现智能体可编辑图表创建
EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
AI 导读
EvoDesign 是一个通过中间画布 schema 实现可编辑图表创建的智能体框架，由结构、样式、布局三个智能体协同构建图表清单，再在诊断验证环境中渲染并生成缺陷信号与 VLM 评述，支持局部精修。
正文 · 原文
Authors:Tianfu Wang, Leilei Ding, Ziyang Tao, Yi Zhan, Zhiyuan Ma, Wei Wu, Yuxuan Lei, Junyang Wang, Yizhao Xu, Yin WU, Zhengyu Hu, Hongyuan Zhu, Nicholas Jing Yuan, Yanyong Zhang, Hui Xiong
Abstract:High-fidelity diagram creation requires coordinated visual-spatial decisions over semantic topology, visual styling, and geometric layout. Existing methods face a representation gap: pixel-based generation offers limited object-level control, while code-based synthesis provides executable structure at the cost of intuitive manipulation. We introduce EvoDesign, an agentic framework for editable diagram creation through an intermediate canvas schema that is both machine-actionable and directly manipulable by users. EvoDesign first constructs a diagram manifest through coordinated structure, style, and layout agents, and then renders the manifest in a diagnostic verification environment. This environment produces objective defect signals and VLM-based critique, enabling localized refinement of the current diagram while also providing evidence for long-term design expertise evolution. The evolution mechanism distills refinement traces into a three-tier design expertise memory, where candidate strategies are linked to the verification evidence that supports them and are promoted into broader guidelines and principles only through repeated cross-context support. We further define CanvasBench, a canvas-recoverable benchmark and evaluation protocol with content, visual, and cognitive dimensions. Experiments across pixel, code-based, agentic, one-shot schema, and canvas-native methods show that EvoDesign provides the strongest overall balance across content fidelity, visual organization, and cognitive usability. Our code is available at this https URL.
| Comments: | Accepted by NeurIPS 2026 |
| Subjects: | Human-Computer Interaction (cs.HC); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2604.09568 [cs.HC] |
| (or arXiv:2604.09568v3 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2604.09568 arXiv-issued DOI via DataCite |
Submission history
From: Tianfu Wang [view email]
[v1]
Fri, 20 Feb 2026 11:11:02 UTC (2,886 KB)
[v2]
Mon, 5 Oct 2026 17:32:59 UTC (2,891 KB)
[v3]
Thu, 5 Nov 2026 18:18:33 UTC (2,724 KB)
来源：arXiv cs.CL · arxiv.org