Wang C, Mu Y, Zhou H, Huo Y, Zhu Z, Zeng J, et al. GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 15];40(39):33395-403. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40626