Do they? How much better are multiple agents on your evals, and what sort of evals are you running? I've also research that suggests that more agents degrades the output after a point.
I think what really degrades the output is the context length vs context window limits, check out NoLima
> coordination yields diminishing or negative returns once single-agent baselines exceed ~45%
This is going to be the big thing to overcome, and without actually measuring it all we're doing is AI astrology.
I agree on measuring and it is planned especially once we integrate the context optimization. I think the value of context optimization will go beyond just avoiding compacting and reducing cost to providing more reliable agents.