BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Denario Project: Multi-Agent Systems for Autonomous Scientific
  Discovery - Boris Bolliet\, Department of Physics
DTSTART:20251027T123000Z
DTEND:20251027T130000Z
UID:TALK237436@talks.cam.ac.uk
CONTACT:Sam Nallaperuma-Herzberg
DESCRIPTION:We present Denario\, an AI multi-agent system designed to be a
  scientific research assistant. Denario can perform many different tasks\,
  such as generating ideas\, checking the literature\, developing research 
 plans\, writing and executing code\, making plots\, and drafting a scienti
 fic paper. Denario is built as a modular system\, and therefore\, can perf
 orm either very specific tasks\, such as generating an idea\, or carrying 
 out end-to-end scientific analysis using Cmbagent (https://github.com/CMBA
 gents/cmbagent) as a deep-research backend. We describe Denario and its mo
 dules in detail and illustrate its capabilities by presenting multiple AI-
 generated papers generated by it. These papers cover many scientific disci
 plines\, such as astrophysics\, biology\, biophysics\, biomedical informat
 ics\, chemistry\, material science\, mathematical physics\, medicine\, and
  planetary science. Denario can also perform research combining ideas from
  different disciplines. We publicly release the code at https://github.com
 /AstroPilot-AI/Denario. A Denario demo can also be run directly on the web
  at https://huggingface.co/spaces/astropilot-ai/Denario\,  and the full ap
 p will be deployed on the cloud.
LOCATION:SS03 Seminar Room\, Willam Gates building (Department of Computer
  Science and Technology)
END:VEVENT
END:VCALENDAR