ThinkPrior: Zero-Rollout Difficulty Priors for Cold-Start Prompt Selection in RLVR
In reinforcement learning with verifiable rewards (RLVR) trained with group relative policy optimization (GRPO), the KL-free reward-advantage term studied here depends on within-group reward variation. If all rollouts in a group are correct or all are wrong, their group-relative advantages are identically zero; these zero-advantage silent groups provide no reward-advantage gradient, yet uniform…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
