@article{tlgrpoturnlevelrlforreasoningguideditera,
  title = {TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization},
  author = {Peiji Li and Linyang Li and Handa Sun and Wenjin Mai and Yongkang Chen and Xiaozhe Li and Yue Shen and Yichuan Ma and Yiliu Sun and Jiaxi Cao and Zhishu He and Bo Wang and Xiaoqing Zheng and Zhaori Bi and Xipeng Qiu and Qipeng Guo and Kai Chen and Dahua Lin},
  year = {2026},
  eprint = {2601.16480},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.16480},
}