@article{distributionawarerewardestimationfortest, title = {Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning}, author = {Bodong Du and Xuanqi Huang and Xiaomeng Li}, year = {2026}, eprint = {2601.21804}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.21804}, }