WANG, Chenglong et al. GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 39, p. 33395–33403, 2026. DOI: 10.1609/aaai.v40i39.40626. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40626. Acesso em: 15 may. 2026.