Jul 2026
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma
Extensive experiments demonstrate that UP enhances exploration capacity and achieves superior reasoning accuracy across diverse RL algorithms (DAPO, GSPO, and GRPO), model architectures, and training modalities, validating UP as a truly universal plug-and-play enhancement for RL-based training.
Chongyu Fan, Pengfei Liu, Jingjia Huang et al.
· arXiv.org · 0 citations