DockSmith:通过代理Docker构建器实现可靠编码环境的扩展
DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder
AI总结:
DockSmith通过代理Docker构建器解决软件工程代理执行基础训练和评估中的可靠环境构建问题,其核心能力涵盖长期工具使用、依赖推理和故障恢复,提升了Docker构建的监督效果。
摘要:
可靠的Docker基础环境构建是扩展执行基础训练和评估软件工程代理的主要瓶颈。我们引入了DockSmith,一种专门的代理Docker构建器,旨在解决这一挑战。DockSmith不仅将环境构建视为预处理步骤,还视为核心代理能力,通过长期工具使用、依赖推理和故障恢复,产生超越Docker构建本身的监督。DockSmith在由SWE-Factory风格流水线增强的大型执行基础Docker构建轨迹上进行训练,使用这些轨迹训练30B-A3B模型在Multi-Docker-Eval上达到开源最先进的性能,具有39.72%的失败到通过率和58.28%的提交率。此外,DockSmith在SWE-bench Verified、SWE-bench Multilingual和Terminal-Bench 2.0上展示了更广泛的代理好处。
英文摘要:
Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address this challenge. DockSmith treats environment construction not only as a preprocessing step, but as a core agentic capability that exercises long-horizon tool use, dependency reasoning, and failure recovery, yielding supervision that transfers beyond Docker building itself. DockSmith is trained on large-scale, execution-grounded Docker-building trajectories produced by a SWE-Factory-style pipeline augmented with a loop-detection controller and a cross-task success memory. Training a 30B-A3B model on these trajectories achieves open-source state-of-the-art performance on Multi-Docker-Eval, with 39.72% Fail-to-Pass and 58.28% Commit Rate. Moreover, DockSmith improves out-of-distribution performance on SWE-bench Verified, SWE-bench Multilingual, and Terminal-Bench 2.0, demonstrating broader agentic benefits of environment construction.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。