BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Rise of Self-Driving Labs: Automation of Scientific Workflows 
 with Agentic Artificial Intelligence - Boris Bolliet - Cavendish Laborator
 y &amp\; Kavli Institute for Cosmology\, University of Cambridge
DTSTART:20250227T130000Z
DTEND:20250227T140000Z
UID:TALK226291@talks.cam.ac.uk
CONTACT:Jack Atkinson
DESCRIPTION:"Agentic" is the word of 2025. Indeed\, multi-agent systems (M
 AS) utilizing multiple Large Language Model agents with Retrieval Augmente
 d Generation and that can execute code locally are becoming beneficial in 
 even the most specialized fields of fundamental research\, like cosmologic
 al data analysis. Here\, we illustrate a first small step towards AI-autom
 ated analyses and a glimpse of the potential of MAS to automate and optimi
 ze scientific workflows in Cosmology. The system architecture of our examp
 le package\, that builds upon the autogen/ag2 framework\, can be applied t
 o MAS in any area of scientific research. The particular task we apply our
  methods to is the cosmological parameter analysis of the Atacama Cosmolog
 y Telescope lensing power spectrum likelihood using Monte Carlo Markov Cha
 ins. Our work-in-progress code is open source and available at https://git
 hub.com/CMBAgents/cmbagent.
LOCATION:West 2\, West Hub
END:VEVENT
END:VCALENDAR