specific method · filed under inference & serving
Medium-effort reasoning mode
A distinct intermediate reasoning mode, described as trained and optimized through supervised fine-tuning and reinforcement learning stages.
- sources
- 2
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
optional 1used 1
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
The medium-effort reasoning mode is introduced during the SFT stage and later optimized during the RLVR stage.
usedpost trainingin Nemotron 3 UltraNVIDIA
Nemotron 3 Ultra is trained for three reasoning modes: reasoning-off, regular and medium-effort.
optionalpost trainingin Nemotron 3 UltraNVIDIA
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 loopParallel-fewest-step samplingQwen3 soft thinking switchTask- and mode-specific sampling parameter recommendationsTest-time compute scalingAdaptive reasoningCapped linear reasoning-token length deductionConfigurable thinking or reasoning modeControllable thinking effort via system message and per-token cost