AI 中文总结
CUA-Sandbox通过分离状态与运行时，实现环境复用，在保持任务成功率的同时，大幅提升回放吞吐量并降低内存和存储成本。
AI 中文摘要
强化学习使计算机使用代理能够通过与真实软件环境（包括网站和桌面应用程序）的交互来改进。然而，传统的部署方式会为每个独立的回放复制一个初始化的运行时，即使轨迹使用相同的软件，随着并行环境数量的增加，也会产生重复的内存和初始化成本。独立的计算机使用环境是否需要独立的执行运行时？我们的关键观察是，轨迹需要独立的可变状态，而初始化的应用程序运行时可以在并发演进的环境之间复用，这使得状态成为环境独立性的自然单位。基于这一观察，我们引入了CUA-Sandbox，它通过状态作用域执行和事务性生命周期操作（包括重置和分支）将私有状态胶囊与共享运行时分离，同时保留原始软件接口和任务评估器。实验表明，与Docker相比，任务成功率相当或有所提高，同时大幅降低了回放和资源成本。CUA-Sandbox实现了高达6.20倍的回放吞吐量提升、每环境内存减少9.2倍，以及增量存储减少504倍。
英文摘要
Reinforcement learning enables computer-use agents to improve through interaction with real software environments, including websites and desktop applications. However, conventional deployments replicate an initialized runtime for each independent rollout, even when trajectories use the same software, incurring repeated memory and initialization costs as the number of parallel environments grows. Does an independent computer-use environment require an independent execution runtime? Our key observation is that trajectories require independent mutable state, while initialized application runtimes can be reused across concurrently evolving environments, making state the natural unit of environment independence. Guided by this observation, we introduce CUA-Sandbox, which separates private state capsules from shared runtimes through state-scoped execution and transactional lifecycle operations, including resets and branches, while retaining the original software interfaces and task evaluators. Experiments show comparable or improved task success relative to Docker, while substantially reducing rollout and resource costs. CUA-Sandbox achieves up to a 6.20x increase in rollout throughput, a 9.2x reduction in per-environment memory, and a 504x reduction in incremental storage.
