#artificial intelligence
May 2026
Rubric-Guided Process Reward for Stepwise Model Routing
Ro is proposed, a rubric-guided process reward framework for stepwise model routing that consistently outperforms strong baselines and achieves better accuracy and cost trade-offs.
Sheng-Hao Ye, Yu Guo, Zheng-Heng Li et al.
· arXiv.org · 2 citations