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

@misc{long2025choice,
  title = {The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward},
  author = {Li Long and Zhijian Zhou and Jiejie Hao and J Liu and Yanting Miao and Wei Pang and Xiaoyu Tan and Wei-Ta Chu and Zhe Wang and Pan, Shirui and Chao Qu and Yuan Qi},
  year = {2025},
  eprint = {2509.07430},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.07430},
}