DERL-MATH-Qwen-2.5-3B

The model for mathematical reasoning task training from MATH training set by DERL.

DERL is introduced in the paper Dual-Evolving Reinforcement Learning for Automated Reward Design.

Paper · Project page · Code

Citation

@misc{cheng2026dualevolvingreinforcementlearningautomated,
      title={Dual-Evolving Reinforcement Learning for Automated Reward Design},
      author={Sitao Cheng and Tianle Li and Xuhan Huang and Xunjian Yin and Difan Zou},
      year={2026},
      eprint={2512.13399},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2512.13399},
}