Overclocking LLM Reasoning
This work investigates how large reasoning models internally track their thinking progress and how such processes can be monitored and controlled. We focus on reasoning models that explicitly segment their computations using <think> and </think> tokens (e.g., DeepSeek-R1), allowing us to study the internal dynamics of the "thinking phase."
1. Monitoring the Thinking Phase
We hypothesize that hidden states encode a token's relative position within the thinking phase. To test this, we collect hidd...
Read more at royeisen.github.io