@article{armadvantagerewardmodelingforlonghorizon,
  title = {ARM: Advantage Reward Modeling for Long-Horizon Manipulation},
  author = {Yiming Mao and Zixi Yu and Weixin Mao and Yinhao Li and Qirui Hu and Zihan Lan and Minzhao Zhu and Hua Chen},
  year = {2026},
  eprint = {2604.03037},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.03037},
}