@article{selfplaywithexecutionfeedbackimproving,
  title = {Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models},
  author = {Guanting Dong and Keming Lu and Chengpeng Li and Tingyu Xia and Bowen Yu and Chang Zhou and Jingren Zhou},
  year = {2024},
  eprint = {2406.13542},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.13542v3},
}