[hrn_frs]

Any attempt at world modeling using today's LLMs needs to have a goal function for the LLM to optimize. The LLM needs to build, evaluate and update it's model of the world. Personally, the main obstacle I found is in updating the model: Data can be large and I think that LLMs aren't good at finding correlations.

[ethbr1]

Isn't that just RL with extra power-intensive steps? (An entire model chugging away in the goal function)

[hrn_frs]

That's correct, but if successful you'd essentially have updated the LLM's knowledge and capabilities "on the fly".