I think the problem will be defining wether there is a cache-hit or not, since "agents" are loosely defined and the tasks include basically anything.
If you boil it down, for a generic enough task and environment, the engine is just a database of previous environments and a user-provided filter function for cache validation
I think the problem will be defining wether there is a cache-hit or not, since "agents" are loosely defined and the tasks include basically anything.