TALK    [MERL Seminar Series 2026] Yuanqi Du presents talk titled Towards Generalist Agents for Accelerating Scientific Discovery

Date & Time:

Wednesday, September 16, 2026; 12:00 PM

Abstract:

Large language models (LLMs) are opening new frontiers in scientific research, enabling capabilities ranging from literature retrieval and hypothesis generation to experimental planning and operation, and bringing us closer to the vision of an AI Scientist. However, it remains unclear what principles should guide the development of such an AI Scientist. In this talk, I will ground this vision in the scientific discovery workflow that drives human progress. First, I will present quantitative evidence of how LLMs are changing the way we search for and validate hypotheses, and how they can serve as powerful tools for hypothesis search. Next, I will discuss how automation can enter the loop by steering the decision-making process. Finally, I will discuss the path toward truly autonomous agents that can operate without any human intervention. These generalist agents are being validated across problems in chemistry, biology, and materials science, including through wet-lab experiments.

Speaker:

Yuanqi Du
Microsoft Research New England

Yuanqi Du is a Senior Researcher at Microsoft Research New England. He received his Ph.D. in Computer Science from Cornell University. His research focuses on developing principled and efficient probabilistic and geometric modeling methods that are inspired by, and accelerate, discovery in the natural sciences, spanning chemistry, physics, and biology. His work has appeared at leading machine learning venues including NeurIPS, ICML, ICLR and in scientific journals including Nature, Nature Machine Intelligence, Nature Computational Science, and the Journal of the American Chemical Society, with three cover articles. His research has been featured by Nature, Science, Chemistry World, Nature Computational Science (Five-Year Anniversary), MIT News, among many others.

MERL Host:

Pu (Perry) Wang

Research Areas:

Artificial Intelligence, Machine Learning