Liu, Wenxuan, Liangyu Huo, Yi Jing, Xiyuan Zhang, and Jian Xie. “MRACL: Multi-Reward Space Guided Adaptive Curriculum Reinforcement Learning for LLMs”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 44 (March 14, 2026): 37663–37672. Accessed May 17, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/41101.