sGPO: Trading Inference FLOPs for Training Efficiency in RLVR 事件

sGPO: Trading Inference FLOPs for Training Efficiency in RLVR arXiv:2606.08854v1 Announce Type: cross Abstract: Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for the current policy. This leads to two symmetric failure modes: easy queries produce near-zero advantage because the policy already solves them, while unsolvable queries produce no signal because the policy ne