@article{tokenhiddenrewardsteeringexplorationexpl,
  title = {Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning},
  author = {Wenlong Deng and Yi Ren and Yushu Li and Boying Gong and Danica J. Sutherland and Xiaoxiao Li and Christos Thrampoulidis},
  year = {2025},
  eprint = {2510.03669},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.03669},
}