I think splitting work across multiple agents is naturally optimal.

The same reasons human designers pick multi agent implementations over monoliths apply to why agents themselves choose to form teams. So there’s a convergence in design choice between human model designers and “self organising AI model designers”.

Those human designers typically publish reasons like the below (paraphrasing various lab publications) , which I imagine the agents also discover:

1) Specialisation reduces cognitive inference 2) Seperate context windows preserve information 3) Independent verification improves reliability 4) Different strategies can be explored concurrently