A Scratchpad and a Controller: Rethinking LLM Reasoning

Reasoning models didn't suddenly grow a new brain. Chain of Thought gives the Transformer an append-only scratchpad, spreading hidden-layer computation across context steps; post-training then builds a Controller that decides when to verify, backtrack, switch paths, or stop. The s1 Wait token, pass@k decay, and Tower of Hanoi tests confirm the Controller's probability re-ranking nature and the physical limits of text-only scratchpads. o1 productized this path, R1 open-sourced it, but the idea started with Scratchpad in 2021.

Why it matters: A reasoning-model explainer with concrete mechanisms and cited experiments, not a survey rehash. Hits all three HKR axes, but as commentary rather than a primary release it lands in the 78–84 band. No cross-source cluster signal, so no bump.