Zhu, X. et al. 2026. PSPO: Prompt-Level Prioritization and Experience-Weighted Smoothing for Efficient Policy Optimization. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 34 (Mar. 2026), 29186–29194. DOI:https://doi.org/10.1609/aaai.v40i34.40157.