@article{atechnicalsurveyofreinforcementlearningt, title = {A Technical Survey of Reinforcement Learning Techniques for Large Language Models}, author = {Saksham Sahai Srivastava and Vaneet Aggarwal}, year = {2025}, eprint = {2507.04136}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.04136}, }