Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage overhead, slow environment setup, and require container-management privileges. We propose SWE-MiniSandbox, a lightweight, container-free method that enables scalable RL training of SWE agents without sacrificing isolation. Instead of relying on per-instance containers, SWE-MiniSandbox executes each task in an isolated workspace backed by kernel-level mechanisms, substantially reducing system overhead. It leverages lightweight environment pre-caching techniques to eliminate the need for bulky container images. As a result, our approach lowers disk usage to approximately 5\% of that required by container-based pipelines and reduces environment preparation time to about 25\% of the container baseline. Empirical results demonstrate that SWE-MiniSandbox achieves evaluation performance comparable to standard container-based pipelines. By removing the dependency on heavy container infrastructure, SWE-MiniSandbox offers a practical and accessible foundation for scaling RL-based SWE agents, particularly in resource-constrained research environments.

翻译：强化学习（RL）已成为训练软件工程（SWE）智能体的核心范式，但现有流水线通常依赖基于每个任务独立容器的隔离机制。在大规模场景下，预构建的容器镜像会产生显著的存储开销、繁琐的环境部署流程，且需要容器管理权限。我们提出SWE-MiniSandbox——一种轻量级无容器方法，可在不牺牲隔离性的前提下实现SWE智能体的可扩展强化学习训练。该方法不依赖基于实例的容器，而是通过内核级机制在每个隔离工作区中执行任务，大幅降低系统开销。通过利用轻量级环境预缓存技术，彻底消除了对臃肿容器镜像的需求。实验表明，相较于基于容器的流水线，本方法可将磁盘使用量降低至约5%，环境准备时间压缩至约25%。实证结果证明，SWE-MiniSandbox可实现与标准容器流水线相当的评估性能。通过消除对重型容器基础设施的依赖，SWE-MiniSandbox为可扩展的强化学习SWE智能体（尤其在资源受限的研究环境中）提供了实用且易用的基础框架。