The View from Nowhere: Population-Centered Agent Evolution
arXiv:2610.36660v2 Announce Type: replace Abstract: Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches center improvement on selected parent agents and their evolutionary experience, leaving the broader population largely underused. We identify a substantial gap between population coverage (i.e., the tasks solved by at least one evolved variant) and the performance of the best individual agent. This gap shows that useful capabilities and dia…