Interesting finding about reasoning models and CoT.

They find that reasoning models can control their chain of thought much better than earlier tests suggested.

Earlier evaluations put the constraint in the user prompt and found very low controllability. Researchers put the same constraint inside the chain of thought as a self-instruction, and models followed it far more often.

A generic reminder to follow the user's constraint also helped a lot. The self-instruction can be triggered from the user prompt alone, so no access to the reasoning channel is needed.

Paper: https://arxiv.org/abs/2610.23257

Chat with Paper: https://academy.dair.ai/papers/reasoning-models-can-control-their-chains-of-thought-when-they-tell-themselves-t-2610.23257