构建百万级可验证的真实代码环境，提升编程智能体训练效果
SWE-Universe: Scale Real-World Verifiable Environments to Millions
- 用自研模型驱动的构建代理，通过自验证和实时漏洞检测确保环境质量
- 生成807,693个真实世界多语言编程环境，规模达百万级
- 助力Qwen3-Max-Thinking在SWE-Bench Verified上取得75.3%准确率
我们提出SWE-Universe，一个可扩展且高效的框架，用于从GitHub拉取请求（PRs）自动构建真实世界软件工程（SWE）可验证环境。为克服自动构建中普遍存在的产出率低、验证器弱、成本高等问题，该框架采用由高效定制模型驱动的构建代理，通过迭代自验证与环内黑客检测，确保高保真、可验证任务的可靠生成。利用此方法，我们将真实世界多语言SWE环境数量扩展至百万量级（807,693个）。通过大规模代理中训练和强化学习，展示了这些环境的巨大价值。最后，将该技术应用于Qwen3-Max-Thinking，在SWE-Bench Verified上达到75.3%的得分。本工作为下一代编码智能体提供了关键资源与稳健方法。
原文摘要 · Abstract (English)
We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic building, such as low production yield, weak verifiers, and prohibitive cost, our framework utilizes a building agent powered by an efficient custom-trained model. This agent employs iterative self-verification and in-loop hacking detection to ensure the reliable generation of high-fidelity, verifiable tasks. Using this method, we scale the number of real-world multilingual SWE environments to a million scale (807,693). We demonstrate the profound value of our environments through large-scale agentic mid-training and reinforcement learning. Finally, we applied this technique to Qwen3-Max-Thinking and achieved a score of 75.3% on SWE-Bench Verified. Our work provides both a critical resource and a robust methodology to advance the next generation of coding agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。