Test-Time Compute (System 2)

What is Test-Time Compute (System 2)?

Test-Time Compute refers to models that spend extra time 'thinking' or generating hidden reasoning tokens during the inference phase before producing a final answer. This approach, similar to human 'System 2' thinking (slow, deliberate), allows models to solve complex problems by exploring multiple paths and verifying steps, effectively trading increased latency for higher intelligence.

Where did the term "Test-Time Compute (System 2)" come from?

Popularized by OpenAI's o1 model and DeepSeek R1 (2024-2025).

How is "Test-Time Compute (System 2)" used today?

Emerging as a new scaling law for reasoning capabilities, shifting focus from pre-training scale to inference-time compute.

Related Terms