Model techniques map
Techniquesinference & servingreasoning control

specific method · filed under inference & serving

Controllable thinking effort via system message and per-token cost

Training varies the system-message effort instruction and per-token cost so rollouts use different amounts of reasoning tokens.

source
1
model
1
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 specified the model’s effort level on different samples by changing the system message and adjusting the per-token cost. This caused the model to use a different amount of tokens in different rollouts and learn the ability to control thinking effort.

usedpost trainingin InklingThinking Machines Lab

Filed alongside

Other methods under inference & serving :: reasoning control.