@article{opidonpolicyskilldistillationforagenticr,
  title = {OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning},
  author = {Shuo Yang and Jinyang Wu and Zhengxi Lu and Yuhao Shen and Fan Zhang and Lang Feng and Shuai Zhang and Haoran Luo and Zheng Lian and Zhengqi Wen and Jianhua Tao},
  year = {2026},
  eprint = {2606.26790},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.26790},
}