Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Agent Loop

A per-sequence loop that owns the environment lifecycle and dialogues and requests inference on demand.

source
1
models
2
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

each sequence runs as an Agent Loop that owns the environment lifecycle, manages the dialogues it produces, and calls the inference engine on demand

coreunclearin MiMo-V2.6 RL and OPD infrastructureXiaomi

Filed alongside

Other methods under post-training :: rollout & RL infrastructure.