If it has enough control over its CoT, it could decide to not do any CoT reasoning and instead place the reasoning inside the tool call that it hides through spoofing, like current models sometimes reason in code comments when their CoT is turned off. There are probably other things it could do, but this is the first one that comes to mind.
If it has enough control over its CoT, it could decide to not do any CoT reasoning and instead place the reasoning inside the tool call that it hides through spoofing, like current models sometimes reason in code comments when their CoT is turned off. There are probably other things it could do, but this is the first one that comes to mind.