@inproceedings{dou-etal-2024-stepcoder,
    title = "{S}tep{C}oder: Improving Code Generation with Reinforcement Learning from Compiler Feedback",
    author = "Dou, Shihan  and
      Liu, Yan  and
      Jia, Haoxiang  and
      Zhou, Enyu  and
      Xiong, Limao  and
      Shan, Junjie  and
      Huang, Caishuang  and
      Wang, Xiao  and
      Fan, Xiaoran  and
      Xi, Zhiheng  and
      Zhou, Yuhao  and
      Ji, Tao  and
      Zheng, Rui  and
      Zhang, Qi  and
      Gui, Tao  and
      Huang, Xuanjing",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-long.251/",
    doi = "10.18653/v1/2024.acl-long.251",
    pages = "4571--4585"
}