@article{efficientreinforcementlearningforlargela,
  title = {Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration},
  author = {Yan Sun and Jia Guo and Stanley Kok and Zihao Wang and Zujie Wen and Zhiqiang Zhang},
  year = {2025},
  eprint = {2511.00794},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.00794},
}