@article{calibrationawarepolicyoptimizationforrea, title = {Calibration-Aware Policy Optimization for Reasoning LLMs}, author = {Ziqi Wang and Xingzhou Lou and Meiqi Wu and Zhengqi Wen and Junge Zhang}, year = {2026}, eprint = {2604.12632}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.12632}, }