@article{canllmsguidetheirownexplorationgradientg,
  title = {Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning},
  author = {Zhenwen Liang and Sidi Lu and Wenhao Yu and Kishan Panaganti and Yujun Zhou and Haitao Mi and Dong Yu},
  year = {2025},
  eprint = {2512.15687},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.15687},
}