We will present how multi-agent systems can be designed to perform scientific research. We will show how we are using them to solve hard open-ended research problems in Cosmology, in some cases outperforming humans operating without them. The agents and systems we develop act as a force multiplier and generate ideas that are novel, but it is important to emphasize that they do not operate in isolation. They augment the humans; they do not replace them. We will then lay out a vision of self-organising AI scientists operating in a parallel cyber space, co-evolving science alongside humans. Finally, we will reflect on what this technology means for science in general and open the floor for discussion.