@article{stepcoderimprovecodegenerationwith,
  title = {StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback},
  author = {Shihan Dou and Yan Liu and Haoxiang Jia and Limao Xiong and Enyu Zhou and Wei Shen and Junjie Shan and Caishuang Huang and Xiao Wang and Xiaoran Fan and Zhiheng Xi and Yuhao Zhou and Tao Ji and Rui Zheng and Qi Zhang and Xuanjing Huang and Tao Gui},
  year = {2024},
  eprint = {2402.01391},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.01391v2},
}