person
Yu Su
Ohio State; AI agents and reasoning
Distinguished assistant professor at Ohio State University; researches reasoning, knowledge graphs, and AI agents. Co-developer of widely-used agent benchmarks.
current Distinguished Assistant Professor, Ohio State University
Strategy positions
Evals-drivenendorses
Capability/risk evals gate deployment; evals are the load-bearing artefactArgues real-world agent evaluations, where the agent must take actions in actual environments, surface different capability and safety properties than synthetic benchmarks.
We benchmark LLM agents on real, live websites. Performance gaps between lab benchmarks and real-world deployment are large, and they reveal where capability claims most often overreach.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Yu Su's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.