AI is now conducting entire medical research loops—from the initial proposal to the final manuscript—without any human help.
Camyla autonomously generates proposals, executes experiments in image segmentation, and writes the complete manuscripts. This moves AI from a research assistant to an autonomous researcher, radically shifting how science can be produced.
Camyla: Scaling Autonomous Research in Medical Image Segmentation
arXiv · 2604.10696
We present Camyla, a system for fully autonomous research within the scientific domain of medical image segmentation. Camyla transforms raw datasets into literature-grounded research proposals, executable experiments, and complete manuscripts without human intervention. Autonomous experimentation over long horizons poses three interrelated challenges: search effort drifts toward unpromising directions, knowledge from earlier trials degrades as context accumulates, and recovery from failures coll