slow-fast-policy-optimization-rl

Stabilize RL for LLM reasoning via three-phase decomposition: fast inner trajectory optimization, repositioning to manage off-policy drift, slow correction for stable updates. Achieve up to 2.80-point math reasoning gains over GRPO while reducing rollouts 4.93x and wall-clock time 4.19x via improved stability without changing reward structure.

Independent GitHub snapshot · Automated classification · Original documentation governs