@article{diversityawarepolicyoptimizationforlarge, title = {Diversity-Aware Policy Optimization for Large Language Model Reasoning}, author = {Jian Yao and Ran Cheng and Xingyu Wu and Jibin Wu and Kay Chen Tan}, year = {2025}, eprint = {2505.23433}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.23433v1}, }