@article{zhang2026klpo,
  title         = {On {KL}-Regularized Policy Optimization},
  author        = {Zhang, Yifan},
  journal       = {arXiv preprint arXiv:2610.08963},
  year          = {2026},
  eprint        = {2610.08963},
  archivePrefix = {arXiv},
  primaryClass  = {cs.LG},
  url           = {https://arxiv.org/abs/2610.08963}
}
