AIM improves research search and reaches baselines up to 3.1× faster
AIM gives an autonomous research system a way to search ideas, check whether experiments tested those ideas, and spend its limited run budget where evidence is most useful. It groups ideas, ranks promising directions, dispatches parallel solvers, then audits the resulting implementations before updating the search. The page says AIM leads the two reported task-group averages, and on Flash Attention it reaches ScientistOne’s best score up to 3.1× faster.