That's definitely around the corner! You should check out the paper [1] I presented at the Wordplay workshop [2] a few weeks ago. The paper discusses automatic evals using LLM agents, but the real fun was actually playing with the model. It brought a whole new experience to an already amazing game!
Wow, this is great! From a quick read through, the structure discussed in the paper is very similar: dialogue trees with fuzzy matching, and actions that materially alter the state and the available options going forward. I have to admit, my tree is a lot shallower right now, though!
(If you want to see what I mean: the alleyway option isn’t available until after you attack the merchant, for example.)
[1]: https://dojoteef.com/papers/virtual_gm_wordplay_2024.pdf
[2]: https://wordplay-workshop.github.io/