Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards 事件

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards arXiv:2602.08499v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner: responses of heterogeneous quality within each prompt are treated uniformly, and historical rollouts are discarded after a