@article{risksensitiverlforalleviatingexploration, title = {Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models}, author = {Yuhua Jiang and Jiawei Huang and Yufeng Yuan and Xin Mao and Yu Yue and Qianchuan Zhao and Lin Yan}, year = {2025}, eprint = {2509.24261}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.24261}, }