Wang, M. et al. 2026. Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 31 (Mar. 2026), 26390–26397. DOI:https://doi.org/10.1609/aaai.v40i31.39845.