@article{curiositydrivenreinforcementlearningfrom, title = {Curiosity-Driven Reinforcement Learning from Human Feedback}, author = {Haoran Sun and Yekun Chai and Shuohuan Wang and Yu Sun and Hua Wu and Haifeng Wang}, year = {2025}, eprint = {2501.11463}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.11463v1}, }