@article{agenticrewardmodelingintegratinghuman,
  title = {Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems},
  author = {Hao Peng and Yunjia Qi and Xiaozhi Wang and Zijun Yao and Bin Xu and Lei Hou and Juanzi Li},
  year = {2025},
  eprint = {2502.19328},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.19328v1},
}