Have you ever worked with a modern agent? They let many weak assumptions slip because their cognitive functions aren't remotely as deep as human's (that's what makes their code a horror), but they have also been trained to hyperfocus on verifying and grounding everything they do and say, you have to actively stop them from doing so when it's unnecessary. This not what I can call confabulation in any good faith, let alone 10% of the time. I think you've been misled by the old paper you cite below, it doesn't say what you likely think it says.