general family · filed under inference & serving
Test-time compute scaling
The broad approach of allocating additional computation at inference time; the evidence does not specify a single scaling algorithm.
Also called test-time scaling, test-time-scaling framework.
- sources
- 2
- models
- 2
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
evaluated 1used 1
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
M3 evaluation: 512k max output tokens, temperature = 1.0, test-time-scaling framework up to 10 iterations.
usedinference servingin MiniMax-M3MiniMax
we evaluate single-agent and multi-agent configurations on both benchmarks under explicit per-rollout wall-clock deadlines.
evaluatedinference servingin 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 recommendationsAdaptive reasoningCapped linear reasoning-token length deductionConfigurable thinking or reasoning modeControllable thinking effort via system message and per-token cost