Jia Guo

Know When to Stop, Where to Restart: Accelerating Multi-Turn Agentic On-Policy Distillation

STRIDE (Stop-and-Restart on-policy Distillation acceleration), which combines two complementary techniques: adaptive early stopping, which terminates a rollout once the cumulative teacher log-probability falls below an out-of-distribution threshold, and a prefix buffer, which caches high-quality prefixes and restarts g...