> In fact, I think in near future it will be the norm for MLLMs to "think" and "reason" without outputting a single "word".

It will be outputting something, as this is the only way it can get more compute - output a token, then all context + the next token is fed through the LLM again. It might not be presented to the user, but that's a different story.

That’s the only effective way to get more compute in current production LLMs, but the field is evolving.