@article{uniformcorrectpolicyoptimizationbreaking, title = {Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity}, author = {Anamika Lochab and Bolian Li and Ruqi Zhang}, year = {2026}, eprint = {2605.00365}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.00365}, }