Provides causal evidence that reasoning models often decide on an action (like a tool call) before they even start generating their 'Chain-of-Thought'.
April 2, 2026
Original Paper
Therefore I am. I Think
arXiv · 2604.01202
The Takeaway
Strongly suggests that reasoning traces are often post-hoc rationalizations rather than the actual computation that drives a decision, fundamentally changing how researchers should interpret 'thinking' in models.
From the abstract
We consider the question: when a large language reasoning model makes a choice, did it think first and then decide to, or decide first and then think? In this paper, we present evidence that detectable, early-encoded decisions shape chain-of-thought in reasoning models. Specifically, we show that a simple linear probe successfully decodes tool-calling decisions from pre-generation activations with very high confidence, and in some cases, even before a single reasoning token is produced. Activati