[1]
Liu, W. et al. 2026. MRACL: Multi-Reward Space Guided Adaptive Curriculum Reinforcement Learning for LLMs. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 44 (Mar. 2026), 37663–37672. DOI:https://doi.org/10.1609/aaai.v40i44.41101.