The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

@misc{li2025choice,
  title = {The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward},
  author = {Long Li and Jiaran Hao and Jason Klein Liu and Zhi-Jian Zhou and Xiao-Yu Tan and Wei Chu and Zhe Wang and Shirui Pan and Chao Qu and Yuan Qi},
  year = {2025},
  eprint = {2509.07430},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.07430},
}