# CoreWeave introduces RL Rollouts for live model weight updates in reinforcement learning

CoreWeave has introduced RL Rollouts, an infrastructure feature that loads new model weights directly into live inference deployments during reinforcement learning without disrupting active requests. NVIDIA and You.com used the feature to post-train Nemotron 3.5 Lightning for web search.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/7d272fee56214976873cd673.html

Content language: en
Localization state: sameLanguage

Source: CoreWeave · Published 10/6/2026, 12:28:58

CoreWeave has launched RL Rollouts to reduce latency during reinforcement learning training loops. Instead of redeploying and pausing the trainer at each checkpoint, the system loads new weights into a live deployment without interrupting in-flight requests, operating roughly 15 times faster than standard redeployment cycles.

NVIDIA and You.com used RL Rollouts to post-train Nemotron 3.5 Lightning for web search. According to CoreWeave's [breakdown](https://crwv.co/utdYc), the workflow raised BrowseComp accuracy from 36.97% to 45.45% while reducing tool calls by 30.24%.

Tags: CoreWeave, Reinforcement Learning, NVIDIA, Nemotron

[View original post](https://x.com/CoreWeave/status/2107552496512094239)