ReDesign：透過代理分解從圖像中還原可編輯設計結構

摘要

从栅格图像中恢复可编辑设计文件，是现代设计工作流中常见且代价高昂的瓶颈，但由于可编辑性依赖于恢复多模态属性（如排版、矢量几何、颜色、分组及图层顺序），这项工作至今仍具挑战性。我们提出ReDesign——一种智能体框架，通过跨模态选择并组合专用工具，逐步构建可编辑的图层层次结构。为使这一长程决策过程在工具输出不完美时仍保持可靠性，我们在每次扩展环节引入优雅验证机制，通过局部接受、修剪或重试反馈，防止错误累积且避免大规模重运行。为在大规模场景下评估可编辑性，我们提出了Figma编辑回放基准测试（Figma Edit Replay Benchmark），包含909个原始Figma文件与14,796条受控编辑指令，可在重建输出上回放编辑操作。在该基准测试及标准重建指标上，ReDesign在实现高视觉保真度的同时，在布局、颜色和文本编辑方面均展现出最优的可编辑性，性能优于基于层次分解的基线方法及串行工具调用管线。

English

Recovering an editable design file from a raster image is a common and costly bottleneck in modern design workflows, yet remains challenging since editability depends on recovering multi-modal attributes, such as typography, vector geometry, colors, grouping, and layer ordering. We present ReDesign, an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities. To keep this long decision process reliable despite imperfect tool outputs, we introduce graceful verification at each expansion, which provides local accept, prune, or retry feedback that prevents error accumulation and avoids large scale reruns. To evaluate editability at scale, we introduce the Figma Edit Replay Benchmark, consisting of 909 raw Figma files and 14,796 controlled edit instructions that replay edits on reconstructed outputs. Across this benchmark and standard reconstruction metrics, ReDesign achieves strong visual fidelity while delivering the highest editability across layout, color, and text edits, outperforming layered decomposition baselines and serial tool use pipelines.