@inproceedings{dou-etal-2025-multi,
    title = "Multi-Programming Language Sandbox for {LLM}s",
    author = "Dou, Shihan  and
      Zhang, Jiazheng  and
      Zang, Jianxiang  and
      Tao, Yunbo  and
      Zhou, Weikang  and
      Jia, Haoxiang  and
      Liu, Shichun  and
      Yang, Yuming  and
      Wu, Shenxi  and
      Xi, Zhiheng  and
      Wu, Muling  and
      Zheng, Rui  and
      Lv, Changze  and
      Xiong, Limao  and
      Zhang, Shaoqing  and
      Zhang, Lin  and
      Zhan, Wenyu  and
      Weng, Rongxiang  and
      Wang, Jingang  and
      Cai, Xunliang  and
      Wu, Yueming  and
      Wen, Ming  and
      Cao, Yixin  and
      Gui, Tao  and
      Qiu, Xipeng  and
      Zhang, Qi  and
      Huang, Xuanjing",
    editor = "Mishra, Pushkar  and
      Muresan, Smaranda  and
      Yu, Tao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-demo.5/",
    pages = "40--50",
    ISBN = "979-8-89176-253-4",
    abstract = "We introduce MPLSandbox, an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). It can automatically identify the programming language of the code, compiling and executing it within an isolated sub-sandbox to ensure safety and stability. In addition, MPLSandbox integrates both traditional and LLM-based code analysis tools, providing a comprehensive analysis of generated code. It also can be effortlessly integrated into the training and deployment of LLMs to improve the quality and correctness of generated code. It also helps researchers streamline their workflows for various LLM-based code-related tasks, reducing the development cost. To validate the effectiveness of MPLSandbox, we conduct extensive experiments by integrating it into several training and deployment scenarios, and employing it to optimize workflows for a wide range of downstream code tasks. Our goal is to enhance researcher productivity on LLM-based code tasks by simplifying and automating workflows through delegation to MPLSandbox."
}