@article{precisionoverdiversityhighprecisionrewar, title = {Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following}, author = {Yirong Zeng and Yufei Liu and Xiao Ding and Yutai Hou and Yuxian Wang and Haonan Song and Wu Ning and Dandan Tu and Qixun Zhang and Bibo Cai and Yuxiang He and Ting Liu}, year = {2026}, eprint = {2601.04954}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.04954}, }