Adobe 测试 AI 智能体能否像专业修图师一样使用 Photoshop 工具
原标题：Adobe is testing how well AI agents can use editing tools like a Photoshop professional would
AI 摘要
Adobe Research 与 UC San Diego 联合构建了 EditAgent，将图像编辑任务拆解为子步骤，让通用编辑器与锐化、缩放等专用工具并行生成多个候选结果，再由标准语言模型借助特写裁剪、变化图和亮度色彩统计等验证记录进行评判。在 600 条编辑基准上，七个语言模型在获得验证记录后全部超越专门微调的评估模型，Qwen3.8-27B 的可用选择率达 81.3%，高于 EditScore-72B 的 74.8%。EditAgent 在三个基准上优于七个其他 AI 智能体，但计算量约为单一编辑器的十倍；其经核验的输出还可生成约 2.6 万条训练样本，用于微调更快的编辑模型。
正文节选
Adobe is testing how well AI agents can use editing tools like a Photoshop professional would Key Points - Adobe Research and UC San Diego built EditAgent, an AI system that breaks image editing tasks into sub-steps and pairs a general-purpose editor with specialized tools for things like sharpening or zooming. - A standard language model evaluates image variants generated in parallel, using measured statistics and close-up crops. With this data, it outperforms evaluation models that were specif