specific method · filed under inference & serving
Reward-optimized preferred reasoning length
The preferred reasoning length is defined by maximizing a reward term minus an effort-dependent token cost.
Also called preferred reasoning length.
- source
- 1
- model
- 1
- labs adopt it
- 0
- strongest
- evaluated
How sources treat it
One count per evidence span, weakest treatment to strongest.
evaluated 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
define the preferred reasoning length ℓ∗x(b) by ℓ∗x(b)∈arg maxℓ≥0 [px(ℓ)−k(b) ℓ/Lnorm]
evaluatedtraining objectivein DeepSeek-V4.1-FlashDeepSeek
Filed alongside
Other methods under inference & serving :: reasoning control.
Configurable reasoning effortChain-of-thought reasoningDefault thinking modeDeployment-time scalar effort controlDisabling reasoning via chat-template configurationInference-time reasoning budget controlInterleaved thinking between tool callsThinking mode selectionCross-turn persistent reasoning historyMaximum thinking effortReasoning parserAlways-on thinking modeclear_thinking chat-template parameterControl-token-enabled thinking modeEffort-dependent exponential token-penalty scheduleGenerate-verify-refine loopMedium-effort reasoning modeParallel-fewest-step samplingQwen3 soft thinking switchTask- and mode-specific sampling parameter recommendationsTest-time compute scalingAdaptive reasoningCapped linear reasoning-token length deductionConfigurable thinking or reasoning mode