Department Colloquium with Francisco Villaescusa-Navarro

Event Date:
2026-10-29T16:00:00
2026-10-29T17:00:00
Event Location:
HENN 200
Speaker:
Francisco Villaescusa-Navarro, Simons Foundation
Related Upcoming Events:
Department Colloquia
Intended Audience:
Everyone
Local Contact:

Brett Gladman (gladman@astro.ubc.ca)

All are welcome to this event!

Event Information:

Title: 

Will the next scientific revolution be driven by AI agents?

Abstract:

Science advances by formulating and testing hypotheses, collecting and analyzing data, and drawing conclusions—yet much of a scientist’s time is spent in tasks such as coding analyses, writing and revising text, reviewing the literature, and learning new concepts. Can recent advances in AI help reclaim some of that time? In this talk, I will show how large language models and AI agents may help scientists with these tasks. I will first describe what AI agents are and discuss their applications in science. Next, I will present Denario, a complex, publicly available, multi-AI-agent system designed to function as a research assistant. Developed and evaluated by a diverse team of scientists, mathematicians, and philosophers, Denario is an interdisciplinary tool capable of generating ideas, searching the literature, developing research plans, writing and executing code, crafting plots, and drafting and reviewing scientific papers. I will also present and discuss some of the papers that Denario generated a couple of years ago in disciplines such as astrophysics, biology, biophysics, biomedical informatics, chemistry, machine learning, materials science, mathematical physics, medicine, neuroscience, planetary physics, and quantum physics. I will then present Denario2, designed to generate scientific knowledge at scale by deploying swarms of AI agents that run autonomously for weeks to months. Finally, I will discuss ethical and philosophical aspects of this kind of research and open a discussion about the role of humans in science.

Bio:

Francisco (Paco) Villaescusa-Navarro is a computational cosmologist and AI researcher whose work aims to transform how scientific discovery is conducted. He has co-led the creation of major cosmological simulation suites—Quijote, CAMELS, DREAMS, and Backlight—that provide the community with petabytes of high-dimensional datasets for precision cosmology and machine learning.

His research develops new theoretical and AI-driven methods to optimally extract information from cosmological data, leveraging simulations to train machine learning models capable of performing fast, accurate inference in highly nonlinear regimes. His work bridges physics-based modeling and data-driven approaches, enabling new ways to analyze large-scale structure, galaxy formation, and survey data.

He is now developing frameworks to integrate multi-agent AI systems into the scientific workflow. As co-creator of Denario, an autonomous AI research companion, he is exploring how agents can generate hypotheses, evaluate literature, design experiments, write and execute code, and assist in scientific writing—reshaping the research process itself.
 

Learn More:

Add to Calendar 2026-10-29T16:00:00 2026-10-29T17:00:00 Department Colloquium with Francisco Villaescusa-Navarro Event Information: Title:  Will the next scientific revolution be driven by AI agents? Abstract: Science advances by formulating and testing hypotheses, collecting and analyzing data, and drawing conclusions—yet much of a scientist’s time is spent in tasks such as coding analyses, writing and revising text, reviewing the literature, and learning new concepts. Can recent advances in AI help reclaim some of that time? In this talk, I will show how large language models and AI agents may help scientists with these tasks. I will first describe what AI agents are and discuss their applications in science. Next, I will present Denario, a complex, publicly available, multi-AI-agent system designed to function as a research assistant. Developed and evaluated by a diverse team of scientists, mathematicians, and philosophers, Denario is an interdisciplinary tool capable of generating ideas, searching the literature, developing research plans, writing and executing code, crafting plots, and drafting and reviewing scientific papers. I will also present and discuss some of the papers that Denario generated a couple of years ago in disciplines such as astrophysics, biology, biophysics, biomedical informatics, chemistry, machine learning, materials science, mathematical physics, medicine, neuroscience, planetary physics, and quantum physics. I will then present Denario2, designed to generate scientific knowledge at scale by deploying swarms of AI agents that run autonomously for weeks to months. Finally, I will discuss ethical and philosophical aspects of this kind of research and open a discussion about the role of humans in science. Bio: Francisco (Paco) Villaescusa-Navarro is a computational cosmologist and AI researcher whose work aims to transform how scientific discovery is conducted. He has co-led the creation of major cosmological simulation suites—Quijote, CAMELS, DREAMS, and Backlight—that provide the community with petabytes of high-dimensional datasets for precision cosmology and machine learning. His research develops new theoretical and AI-driven methods to optimally extract information from cosmological data, leveraging simulations to train machine learning models capable of performing fast, accurate inference in highly nonlinear regimes. His work bridges physics-based modeling and data-driven approaches, enabling new ways to analyze large-scale structure, galaxy formation, and survey data. He is now developing frameworks to integrate multi-agent AI systems into the scientific workflow. As co-creator of Denario, an autonomous AI research companion, he is exploring how agents can generate hypotheses, evaluate literature, design experiments, write and execute code, and assist in scientific writing—reshaping the research process itself.  Learn More: Read his profile from the Simons Foundation website: https://www.simonsfoundation.org/people/francisco-villaescusa-navarro/  See his personal website here: https://franciscovillaescusa.github.io/ Read Simons Foundation Center for Computational Astrophysics FlatIron Institute article, "Artificial Intelligence Discovers Secret Equation for ‘Weighing’ Galaxy Clusters": https://www.simonsfoundation.org/2023/03/23/artificial-intelligence-discovers-secret-equation-for-weighing-galaxy-clusters/     Event Location: HENN 200