Project Grant 2624051

The National Science Foundation Office of Advanced Cyberinfrastructure awarded The Research Foundation for the State University of New York $120,500 on October 1, 2026, for disciplinary improvements in agentic materials research under the Computer and Information Science and Engineering program (CFDA 47.070).

The project will establish technical foundations for trustworthy agentic science in materials research by developing three coupled elements: machine-actionable context specifications that capture entities, provenance, life-cycle stages, governance constraints, and repository expectations needed for reliable automated action on materials data and models; a curated library of reusable agentic skills as bounded, testable modules following formal contracts for recurring FAIR and research-data-management operations including metadata extraction, schema crosswalk, provenance capture, FAIR packaging, and quality assessment; and benchmark suites and scoring protocols that evaluate whether agentic systems can perform realistic materials-research tasks with consistency, reproducibility, and scientific fidelity. The project addresses the central bottleneck that current AI-enabled workflows in data-intensive materials research remain difficult to trust, reproduce, and reuse across instruments, laboratories, and organizations because scientific context needed for reliable automated action is fragmented, inconsistently represented, and rarely benchmarked.

Performance takes place in Buffalo, New York, with a period of performance from October 1, 2026, through September 30, 2029. The Research Foundation administers the award as the fiscal agent for the State University of New York system.