LIU, Wenxuan; HUO, Liangyu; JING, Yi; ZHANG, Xiyuan; XIE, Jian. MRACL: Multi-Reward Space Guided Adaptive Curriculum Reinforcement Learning for LLMs. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 37663–37672, 2026. DOI: 10.1609/aaai.v40i44.41101. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41101. Acesso em: 17 may. 2026.