@article{t2pouncertaintyguidedexplorationcontrolf,
  title = {T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning},
  author = {Haixin Wang and Hejie Cui and Chenwei Zhang and Xin Liu and Shuowei Jin and Shijie Geng and Xinyang Zhang and Nasser Zalmout and Zhenyu Shi and Yizhou Sun},
  year = {2026},
  eprint = {2605.02178},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.02178},
}