The Rise Of Reasoner Models: Scaling Test-Time Compute

A new kind of LLM has recently been popping out everywhere: Reasoner models. Kickstarted by OpenAI's o1 and o3, these models are a bit different from the rest. These models particularly shine when dealing with mathematical problems and coding challenges, where success depends on following precise, logical steps to reach a correct solution. On the other hand, these models take much longer to answer than any conventional model.

The approach to problem-solving used by these models mirrors a well-known distinction in human cognition: System 1 versus System 2 thinking. Traditional LLMs operate much like System 1 thinking — quick, intuitive, and based on pattern recognition. They generate responses rapidly based on their trained neural networks. In contrast, Reasoner models embody System 2 thinking — deliberate, methodical, and self-correcting. They can pause, reflect on their reasoning, and even backtrack when they detect potential errors in their logic.