@article{improvingdataefficiencyforllm,
  title = {Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay},
  author = {Yifan Sun and Jingyan Shen and Yibin Wang and Tianyu Chen and Zhendong Wang and Mingyuan Zhou and huan zhang},
  year = {2025},
  eprint = {2506.05316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.05316v1},
}