Heapa: Difficulty-aware heap sampling and on-policy query augmentation for llm reinforcement learning.arXiv preprint arXiv:2601.22448

Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui, Rongzhi Zhang, Changlong Yu, Shuowei Jin, Jingfeng Yang, Qingyu Yin, Zhengyang Wang, et al · arXiv 2601.22448