@article{whenselfbeliefmisleadsactivelabelacquisi, title = {When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards}, author = {Li Wang and Xiaodong Lu and Xiaohan Wang and Yikun Ban and Jiajun Chai and Wei Lin and Tianhao Peng and Guojun Yin}, year = {2026}, eprint = {2605.25864}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.25864}, }