Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR 事件

Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR arXiv:2605.28295v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the policy to alternative reasoning paths and a verifier to score them. Rollout diversity has accordingly emerged as a central bottleneck in RLVR, with most existing methods broadening exploration through temperature, pr