Model techniques map
Techniquespost-trainingrollout & RL infrastructure

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.