arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.09568cs.HCcs.CLcs.CV
收藏

EvoDiagram:通过设计专业知识进化实现代理可编辑的图示创建

EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution

Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));University of Science and Technology of China(中国科学技术大学);Peking University(北京大学)
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, Ya… 展开作者

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

AI总结:

EvoDiagram通过设计专业知识进化实现代理可编辑图示创建,解决自动系统在高保真图示生成中的挑战,提出中间画布方案和设计知识进化机制,释放CanvasBench基准测试。

摘要:

高保真图示创建需要复杂的语义拓扑、视觉样式和空间布局的协调,对自动系统构成重大挑战。现有方法存在表示鸿沟:基于像素的模型缺乏精确控制,基于代码的合成限制直观灵活性。为弥合这一鸿沟,我们引入EvoDiagram,一种代理框架,通过中间画布方案生成对象级可编辑图示。EvoDiagram采用协调的多代理系统,将语义意图与渲染逻辑解耦,解决异构设计层间的冲突。此外,我们提出设计知识进化机制,将执行轨迹提炼为领域指南的分层记忆,使代理能够适应性检索上下文感知的专业知识。我们进一步发布CanvasBench,一个包含数据和指标的画布图示基准测试。广泛实验表明,EvoDiagram在生成可编辑、结构一致且视觉协调的图示方面表现出色。我们的代码可在https://github.com/AuraX-AI/EvoDiagram获取。

英文摘要:

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 https://github.com/GeminiLight/EvoDesign.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑