Victor Zhong, Jimmy Lin awarded $1.64M NSERC Alliance grant to develop deep research agents for natural science R&D
Professor Victor Zhong (principal investigator) and Professor Jimmy Lin (co-investigator) of the Cheriton School of Computer Science have been awarded $1,641,776 through the NSERC Alliance Grant program. Combined with more than $1.8 million in cash and in-kind contributions from industry partner BASF Canada, the total project value reaches roughly $3.5 million.
The three-year project, titled “Deep Research Agents for Natural Science R&D,” will co-develop and deploy an end-to-end intelligent research assistant capable of retrieving, reasoning over, and acting on diverse experimental data sources. Developed with BASF Canada, it aims to transform chemical informatics from static information retrieval into dynamic, action-oriented knowledge systems that accelerate scientific discovery.
The project will also help train the next generation of researchers, supporting two postdoctoral researchers, six PhD students and two master’s students over its three years.
More about this research
Innovation in the chemical sciences requires integrating diverse data sources — from reaction protocols and compound properties to safety data sheets and spectral data — that are often stored across separate, incompatible systems. As a result, researchers can spend a significant share of their time retrieving, cleaning and integrating data manually rather than focusing on discovery.
Overcoming these barriers requires AI systems that can reason across diverse information sources and interact seamlessly with laboratory data. Current methods fall short: retrieval-augmented generation systems struggle with complex hybrid scientific queries, while text-to-SQL systems require rigid schemas poorly suited to unstructured lab notes. This project aims to develop a multimodal, general-purpose agent equipped with computer vision and logical reasoning to support experimental planning — a step toward autonomous scientific execution.
Professor Zhong contributes expertise in frontier agentic behaviours and reasoning, while Professor Lin brings expertise in scalable retrieval infrastructure to enable efficient processing of the large, complex datasets involved in industrial R&D.
p>
