Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
Read full paper →- Authors
- Shuo Yang, Jinda Lu, Chiyu Ma, Kexin Huang, Haoming Meng, Qihui Zhang, Yuyang Liu, Bolin Ding, Guoyin Wang, Li Yuan, Jingren Zhou
- Year
- 2026