specific method · filed under post-training
Tool Manager
Coordinates with Toolbox for environment pre-warming and sequence-level asynchronous reward computation.
- 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.
Tool Manager combined with Toolbox
usedsoftware implementationin MiMo-V2-FlashXiaomi
Tool Manager coordinates with Toolbox to accelerate training through environment pre-warming and sequence-level asynchronous reward computation.
usedsoftware implementationin MiMo-V2-FlashXiaomi
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 schedulingLarge-scale asynchronous RL in synthesized tasksOne-step off-policy asynchronous reinforcement learningPredictive Rollout DispatchSample-grained garbage collectionSeamless Rollout EngineSLIMEToken-granularity persistence of rollout statesToken-level interruptionToolboxAdaptive Rollout ConcurrencyAdaptive Rollout SchedulingAgent LoopAgent-centric rollout executionAsynchronous Agent RL algorithms