SWE-Master：通过训练后技术释放软件工程代理的潜力
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
AI总结：
SWE-Master通过训练后技术提升软件工程代理能力，实现61.4%的解决率并优于现有基线。
摘要：
本文技术报告中，我们介绍了SWE-Master，一个开源且完全可复现的训练后框架，用于构建有效的软件工程代理。SWE-Master系统性地探索了完整的代理开发流程，包括教师轨迹合成与数据整理、长 horizon 的SFT、具有真实执行反馈的强化学习以及推理框架设计。从一个具有有限初始SWE能力的开源基础模型出发，SWE-Master展示了系统性优化方法如何激发强大的长 horizon SWE任务解决能力。我们在SWE-bench Verified上评估了SWE-Master，这是一个用于现实软件工程任务的标准基准。在相同的实验设置下，我们的方法在Qwen2.5-Coder-32B上达到了61.4%的解决率，显著优于现有的开源基线。通过进一步结合测试时扩展（TTS）与基于LLM的环境反馈，SWE-Master在TTS@8时达到了70.8%，展示了强大的性能潜力。SWE-Master为推进可复现的软件工程代理研究提供了实用且透明的基础。代码可在https://github.com/RUCAIBox/SWE-Master上获得。
英文摘要：
In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4\% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8\% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.
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。
