Agents for Scientific Discovery: A Parallel Universe?
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 some cases outperforming humans operating without them. The agents and systems we develop act as a force multiplier and generate ideas that are novel to us, 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.
Zoom Details
Zoom Link:
https://berkeley.zoom.us/j/95637909214?pwd=Ud2TwBvogrHyHZoMD3Dn6rxEAGyPKU.1
Meeting ID: 956 3790 9214
Passcode: 856266
Our Speaker:
Boris Bolliet
Boris helped introduce multi-agent systems in Astrophysics with his work on Cmbagent (starting in 2024). He now works across disciplines, developing systems that can automate parts of the research process and accelerate discovery. Boris is based in Cambridge where he teaches in the MPhil in Data Intensive Science. He is one of the creators of Denario .