HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning

published

Cite this paper

@article{yucan2026,
  title = {HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning},
  author = {Guo, Yucan and Wang, Xiaohan and Su, Miao and Guan, Saiping and Hou, Zhongni and Chai, Jiajun and Lin, Wei and Yin, Guojun and Jin, Xiaolong and Guo, Jiafeng and Cheng, Xueqi},
  journal = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year = {2026},
  month = {Jan},
  doi = {10.18653/2026.findings-emnlp.299},
  url = {https://doi.org/10.18653/2026.findings-emnlp.299},
}