I don't know of any that use LLMs and my educated opinion would be that there won't be any in the next decade or ever. The main reasons are that games already run with tight margins of both frame time and memory consumption, and that designers/game developers want to control the interactions with the player and what the player experiences in the game. So an LLM won't be used for any story relevant NPCs in the game as what they say is tightly curated, and it's never going to be good/fast/slim enough to get used for crowd NPCs.

Using machine learning to make enemies smarter has been thought about and talked about for decades, but I don't see it being used either for similar reasons. Training a ML algorithm takes resources which are in short supply and time which could take longer than for the player to finish the game (if you want smarter enemies play against real human players). There's also the fact that the game has to run on the minimum specification computer, which means different players will have differently skilled enemies and their experience of the game will suffer.

There have been some games in the past which used some form of machine learning as a core gameplay feature, but they have been pet breeding simulators.