no surprise that clones of the same model massively underperform
cognitive diversity is what makes multi-agent systems work so effectively
when people work together, diversity allows us to nicheify and thus span the whole space.
More evidence that at least for now, multi-agent systems don't solve anything that single-agent systems can't, they just get to the same results faster.
I do think this could change in the future, but for now multi-agent systems aren't any more powerful than single-agent ones.