AI 学用电脑，终于不用靠真人录屏了
训练 AI 学会操作电脑(点按钮、填表单、开软件)一直卡在同一个地方：没有足够多的真实软件给它练手，而人工录屏又贵又慢。这篇论文换了个思路——干脆让 AI 自己批量生成假的软件界面，再让另一个 AI 去检查这些假软件能不能真的跑起来，不行就修，直到能用为止。用这套流水线，他们造出了 182 个覆盖 12 类场景的假软件，拿这些环境训练出来的 AI，在完全没见过的真实软件测试上，成功率从 41% 提到了 57%。它不是你明天就能用上的东西，但它指向一个更省钱的训练方向：与其攒真实数据，不如批量造可控的练习场。
📄 原文摘要(英文)
Computer-use agents (CUAs) are rapidly improving, yet synthesizing diverse and reliable software environments at scale remains challenging. Native application environments require substantial construction and integration effort, which limits application coverage and increases the risk of application-specific overfitting. Browser-hosted environments provide limited interaction depth and workflow complexity. These limitations motivate SoftwareGym, an automated pipeline for synthesizing GUI software environments with diverse interfaces, executable functionality, and runtime-verified behavior. It generates structurally diverse designs, realizes them as runnable applications, and uses GUI evaluation with iterative repair to ensure functional reliability. Using SoftwareGym, we synthesize 182 applications across twelve categories and achieve a mean GUI task pass rate of 91.5%. We construct SoftwareGym-Bench, a 120-task evaluation suite spanning the same twelve categories, and use trajectories collected from these environments for CUA training. The resulting model improves Pass@3 from 41.39% to 56.97% on the strictly out-of-domain OSWorld benchmark and achieves 40.0% on SoftwareGym-Bench. These results demonstrate the potential of synthesized software environments as scalable and transferable supervision for CUA training.