The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration
Reinforcement learning with verifiable rewards (RLVR) is often limited by insufficient exploration: difficult problems can yield uniformly incorrect rollout groups and therefore little learning signal. We show that such failures need not reflect missing capability. Instead, finite sampling often concentrates on a probl...
Jin Cui, Xin-Yue Long, Bo-Ran Zhao et al.
· 0 citations