Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Heterogeneous Agent Harnesses

Configures harness codebases, agent behavior, and environment settings separately to support diverse tasks in one training run.

source
1
models
2
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

We configure harness codebases, agent behavior, and environment settings separately to accommodate diverse tasks within a single training run.

usedunclearin MiMo-V2.6 RL and OPD infrastructureXiaomi

Filed alongside

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