@article{improvingrlexplorationforllmreasoning,
  title = {Improving RL Exploration for LLM Reasoning through Retrospective Replay},
  author = {Shihan Dou and Muling Wu and Jingwen Xu and Rui Zheng and Tao Gui and Qi Zhang and Xuanjing Huang},
  year = {2025},
  eprint = {2504.14363},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.14363v1},
}