specific method · filed under post-training
Large-scale asynchronous RL in synthesized tasks
Uses large-scale asynchronous RL on synthesized tasks to shape behavior in complicated scenarios.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
We use large-scale asynchronous RL in synthesized tasks to improve model performance and shape its behavior in complicated scenarios.
usedunclearin DeepSeek-V4.1-FlashDeepSeek
We use large-scale asynchronous RL in synthesized tasks to improve model performance and shape its behavior in complicated scenarios.
usedpost trainingin DeepSeek-V4.1DeepSeek
Filed alongside
Other methods under post-training :: rollout & RL infrastructure.
Asynchronous reinforcement learningPartial rolloutAsynchronous RL frameworks for large-scale agent scaffolds and environment orchestrationToken-in-token-out (TITO)Asynchronous reinforcement learning infrastructureCo-located RL trainingData SchedulerDecoupled control plane and data planeDecoupling agent rollout into sandbox and worker containerDeficit-corrected schedulingOne-step off-policy asynchronous reinforcement learningPredictive Rollout DispatchSample-grained garbage collectionSeamless Rollout EngineSLIMEToken-granularity persistence of rollout statesToken-level interruptionTool ManagerToolboxAdaptive Rollout ConcurrencyAdaptive Rollout SchedulingAgent LoopAgent-centric rollout executionAsynchronous Agent RL algorithms