Model techniques map
Techniquespost-trainingagentic post-training

specific method · filed under post-training

Production-harness-matched reinforcement learning

Reinforcement learning rollouts use the same harness, tool API, chat template, and orchestration layer as production.

source
1
model
1
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.

The harness driving RL rollouts is the same one we ship in production: the policy interacts through the same tool API, chat template, and orchestration layer that customers exercise

corepost trainingin Laguna XS.2Poolside

Filed alongside

Other methods under post-training :: agentic post-training.