@article{rlfinetuningllmsfromonandoffpolicy,
  title = {RL-finetuning LLMs from on- and off-policy data with a single algorithm},
  author = {Yunhao Tang and Taco Cohen and David W. Zhang and Michal Valko and Rémi Munos},
  year = {2025},
  eprint = {2503.19612},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.19612v2},
}