Computer-use agents hold the promise of assisting in a wide range of digital economic activities. However, current research has largely focused on short-horizon tasks over a limited set of software with limited economic value, such as basic e-commerce and OS-configuration tasks. A key reason is that creating environments for complex software requires significant time and human effort, and therefore does not scale. To address this, we introduce Gym-Anything, a framework for converting any software into an interactive computer-use environment. We frame environment creation itself as a multi-agent task: a coding agent writes setup scripts, downloads real-world data, and configures the software, while producing evidence of correct setup. An independent audit agent then verifies evidence for the environment setup against a quality checklist. Using a taxonomy of economically valuable occupations grounded in U.S. GDP data, we apply this pipeline to 200 software applications with broad occupational coverage. The result is CUA-World, a collection of over 10K long-horizon tasks spanning domains from medical science and astronomy to engineering and enterprise systems, each configured with realistic data along with train and test splits. CUA-World also includes CUA-World-Long, a challenging long-horizon benchmark with tasks often requiring over 500 steps, far exceeding existing benchmarks. Distilling successful trajectories from the training split into a 2B vision-language model outperforms models 2$\times$ its size. We also apply the same auditing principle at test time: a separate VLM reviews completed trajectories and provides feedback on what remains, improving Gemini-3-Flash on CUA-World-Long from 11.5% to 14.0%. We release all code, infrastructure, and benchmark data to facilitate future research in realistic computer-use agents.

翻译：计算机使用智能体有望在广泛的数字经济活动提供辅助。然而，现有研究主要聚焦于有限软件集合中的短周期任务，且这些任务的经济价值有限，例如基础电子商务和操作系统配置任务。究其原因，为复杂软件创建环境需要大量时间和人力投入，因而难以规模化。为解决此问题，我们提出Gym-Anything，一个将任意软件转化为可交互计算机使用环境的框架。我们将环境创建本身构建为多智能体任务：一个编程智能体编写配置脚本、下载真实世界数据并配置软件，同时生成正确配置的证据。随后，一个独立的审计智能体根据质量检查清单验证环境配置的证据。基于美国GDP数据中具有经济价值的职业分类体系，我们将此流程应用于覆盖广泛职业的200个软件应用。最终成果是CUA-World，一个包含超过1万个长周期任务的集合，覆盖从医学科学、天文学到工程与企业系统等多个领域，每个任务均配置有真实数据及训练/测试拆分。CUA-World还包含CUA-World-Long，一个极具挑战性的长周期基准，其任务常需超过500步才能完成，远超现有基准。从训练拆分中蒸馏成功轨迹并注入2B视觉-语言模型后，该模型性能超越了参数规模为其2倍的模型。我们还在测试时应用相同的审计原则：独立的视觉语言模型审查已完成轨迹并提供待完成项的反馈，使Gemini-3-Flash在CUA-World-Long上的性能从11.5%提升至14.0%。为促进未来对真实计算机使用智能体的研究，我们开源了所有代码、基础设施及基准数据。