El Agente está presente: The era of AI scientists | In-person

Join us for MScAC Talks, a yearly speaker series where academic and industry leaders share applied research driving real-world advances at the University of Toronto.

Abstract

We stand at the inflection point of Agentic Science, where AI transitions from a passive generator to an active reasoning engine capable of autonomous discovery. The challenge of scientific research—characterized by heterogeneous tools, high-dimensional search spaces, and strict physical constraints—demands systems capable of long-horizon planning and rigorous self-correction. In this keynote, I unveil the El Agente ecosystem, a unified cognitive architecture designed to automate the full research lifecycle.

Moving beyond standard chain-of-thought prompting, we introduce a hierarchical multi-agent framework that solves the "tool-use bottleneck" through dynamic planning and modular memory. I will discuss how we engineer agents capable of Guided Deep Research—a novel runtime retrieval mechanism that enables systems to parse complex technical documentation and synthesize code for heterogeneous simulation environments on which they were not explicitly trained. Furthermore, we address the grand challenge of spatial reasoning by grounding vision-language models in precise 3D Euclidean tools, bridging the gap between generative intent and physical constraints. This architecture represents a blueprint for the next generation of AI: systems that not only assist but also collaborate, reason, and discover.

Speaker Biography

Alán Aspuru-Guzik is a Professor at the University of Toronto, with primary appointments in the Departments of Chemistry and Computer Science and cross-appointments in Chemical Engineering and Applied Chemistry, Materials Science and Engineering, and the Institute of Medical Science. He is Senior Director at NVIDIA Research, CIFAR AI Chair at the Vector Institute for Artificial Intelligence, Director of the Acceleration Consortium, and Co-Director of the CIFAR Accelerated Decarbonization program. His research centers on the integration of artificial intelligence, automation, and the natural sciences, with applications spanning functional materials, robotics, and quantum computing. He is Editor-in-Chief of the Royal Society of Chemistry journal Digital Discovery and Fellow of the Royal Society of Canada.

Alán began his independent career at Harvard University in 2006 and was a full professor there from 2013 to 2018. He received his B.Sc. from the National Autonomous University of Mexico (UNAM) in 1999 and his PhD from the University of California, Berkeley in 2004, where he joined as a postdoctoral fellow from 2005 to 2006.

Alán conducts research in the interfaces of quantum information, machine learning, and chemistry. He was a pioneer in the development of algorithms and experimental implementations of quantum computers and quantum simulators dedicated to chemical systems. He has studied the role of quantum coherence in the transfer of excitonic energy in photosynthetic complexes, and accelerated the discovery by calculating organic semiconductors, organic photovoltaic energy, organic batteries, and organic light-emitting diodes. He has worked on molecular representations and generative models for the automatic learning of molecular properties. Currently, Alán is interested in automation and “autonomous” chemical laboratories for accelerating scientific discovery.

Among other recognitions, he received the Schmidt Science AI2050 Senior Fellowship, Google Focused Award for Quantum Computing, the Sloan Research Fellowship, and the Camille and Henry Dreyfus Teacher-Scholar Award. He was the Winner of the Heinrich Emanuel Merck Award for Innovations in the Computational Sciences in 2025. Alán was selected as one of the best innovators under the age of 35 by the MIT Technology Review. He is an elected fellow of the American Physical Society, an elected fellow of the American Association for the Advancement of Science (AAAS), and received the Early Career Award in Theoretical Chemistry from the American Chemical Society. Alán appeared as one of the top 100 most powerful Canadians in 2024 by the Maclean’s Magazine under the AI Category.

Alán is the co-founder of Zapata AI, Kebotix, Intrepid Labs, and Axiomatic AI.

See also Alán's profile at the Discover Research Portal at the University of Toronto for current media, research, and awards.

Affiliations

Department of Computer Science
University of Toronto, 40 St George St., Toronto, ON M5S 2E4, Canada

Department of Chemistry
University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada

Department of Chemical Engineering & Applied Chemistry
University of Toronto, 200 College St., Toronto, ON M5S 3E5, Canada

Department of Materials Science & Engineering
University of Toronto, 184 College St., Toronto, ON M5S 3E4, Canada

Institute of Medical Science
University of Toronto, 1 King's College Circle, Medical Sciences Building, Room 2374, Toronto, ON M5S 1A8, Canada

Vector Institute for Artificial Intelligence
W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON M5G 0C6, Canada

Acceleration Consortium
700 University Ave., Toronto, ON M7A 2S4, Canada

Canadian Institute for Advanced Research (CIFAR)
661 University Ave., Toronto, ON M5G 1M1, Canada

NVIDIA
431 King St. W #6th, Toronto, ON M5V 1K4, Canada

About the MSc in Applied Computing Program

Housed in the Department of Computer Science at the University of Toronto, the Master of Science in Applied Computing (MScAC) program is committed to educating the next generation of world-class innovators. The program bridges cutting-edge research with industry innovation, equipping students to translate ideas into real-world solutions. By fostering collaboration among students, faculty, alumni, and industry partners, MScAC creates a vibrant community where research excellence drives meaningful impact.

Know what’s Happening Next — before everyone else does.

Get App

Host or Publisher Master of Science in Applied Computing @ UofT