@article{zhang2026rewardharness,
  title={RewardHarness: Self-Evolving Agentic Post-Training},
  author={Zhang, Yuxuan and Du, Penghui and Li, Bo and Wei, Cong and Miao, Junwen and Zhang, Huaisong and Cai, Songcheng and Wang, Yubo and Jiang, Dongfu and Zhang, Yuyu and others},
  journal={arXiv preprint arXiv:2605.08703},
  year={2026}
}
