What even are these new "decision models?" Take an existing LLM, feed it a prompt, force it to pick a choice; decode is 1 token (or rather, the whole logit set for only that last token; token implies selecting one logit) so you made a choice. That's it?

Yes, although you probably want to calibrate your model if you want the probabilities to actually be meaningful.

Yes but optimized specifically for the purpose. Using that for "decision making" is also not a new use case, but turned out to be new to many people. Which is great, I hope they make something cool with it!

That's how Cygnet handles it.

https://github.com/blockbrain-ai/cygnet-recipe