LI, W.; WANG, J.; YU, L.-C.; ZHANG, X. Step-GRPO: Enhancing Reasoning Quality and Efficiency via Structured PRM-Based Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 37, p. 31734-31742, 2026. DOI: 10.1609/aaai.v40i37.40441. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40441. Acesso em: 1 may. 2026.