Feng X, Jiang Z, Kaufmann T, Xu P, Hüllermeier E, Weng P, et al. DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 8];39(16):16604-12. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/33824