用智能体框架生成可编辑的高质量图表，支持精准控制与自动优化。
EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
- 采用多智能体系统分离语义意图与渲染逻辑，实现分层协同设计。
- 通过执行轨迹提炼出层次化设计知识库，提升智能体自适应能力。
- 适合需要高精度、可修改图表的科研与工程场景。
高保真图表生成需协调语义拓扑、视觉风格与空间布局，对自动化系统构成挑战。现有方法存在表示鸿沟：像素模型难以精确控制，代码生成又缺乏直观灵活性。为此，我们提出EvoDiagram，一个基于中间画布模式的智能体框架，通过多智能体协作将语义意图与渲染逻辑解耦，解决异构设计层间的冲突。我们还引入设计知识演化机制，将执行轨迹提炼为分层领域规则记忆，使智能体可自适应检索上下文相关专业知识。此外，我们发布了CanvasBench基准，包含数据集和画布式绘图评估指标。大量实验表明，EvoDiagram在生成可编辑、结构一致且美学协调的图表方面优于基线方法。代码已开源：https://github.com/AuraX-AI/EvoDiagram。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。