SOURCE-LINKED INTELLIGENCE

Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

RL-based post-training for reasoning models is increasingly bottlenecked by repeated fresh rollout generation, particularly in agentic settings where environment interaction dominates wall-clock cost. Replay can reduce this burden by reusing past trajectories, but existing methods typically embed it within larger training pipelines involving exploration, experience restructuring, or mixed-policy optimization. This makes replay's own contribution difficult to isolate. We ask a focused question: how far can principled replay selection alone go? We introduce Headroom-Drift Replay, a group-level r

Read original source ↗ Open in workspace

recordType

paper

region

Global