@article{reasoninchainslearnintreesselfrectificat,
  title = {Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization},
  author = {Yu Li and Sizhe Tang and Tian Lan},
  year = {2026},
  eprint = {2604.07165},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.07165},
}