The Rise of Self-Driving Labs: Automation of Scientific Workflows with Agentic AI - Boris Bolliet скачать в хорошем качестве

The Rise of Self-Driving Labs: Automation of Scientific Workflows with Agentic AI - Boris Bolliet

Presenter: Boris Bolliet, Cavendish Laboratory & Kavli Institute for Cosmology, University of Cambridge Presented on: 2025-02-27 Abstract: “Agentic” is the word of 2025. Indeed, multi-agent systems (MAS) utilizing multiple Large Language Model agents with Retrieval Augmented Generation and that can execute code locally are becoming beneficial in even the most specialized fields of fundamental research, like cosmological data analysis. Here, we illustrate a first small step towards AI-automated analyses and a glimpse of the potential of MAS to automate and optimize scientific workflows in Cosmology. The system architecture of our example package, that builds upon the autogen/ag2 framework, can be applied to MAS in any area of scientific research. The particular task we apply our methods to is the cosmological parameter analysis of the Atacama Cosmology Telescope lensing power spectrum likelihood using Monte Carlo Markov Chains. Our work-in-progress code is open source and available at https://github.com/CMBAgents/cmbagent.