ThinkPrior: Zero-Rollout Difficulty Priors for Cold-Start Prompt Selection in RLVR
ThinkPrior builds zero-rollout difficulty priors via an offline verifier-anchored pass, halving silent groups in RLVR and cutting wasted rollouts on Qwen2.5-Math-7B.
1 stories, newest first · one card per story
ThinkPrior builds zero-rollout difficulty priors via an offline verifier-anchored pass, halving silent groups in RLVR and cutting wasted rollouts on Qwen2.5-Math-7B.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views