@article{hintguideddiversifiedpolicyoptimizationf, title = {Hint-Guided Diversified Policy Optimization for LLM Reasoning}, author = {Zhiyu Cao and Kaixin Wu and Mingjie Zhong and Peifeng Li and Xiaobo Li and Can Ye and Qiaoming Zhu}, year = {2026}, eprint = {2606.03021}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.03021}, }