Three agents share data to autonomously control a lab and design high-activity enzymes

KevinKaichuang · x · 2026-08-21

Researchers demonstrated a closed-loop framework where autonomous agents design protein variants, construct and characterize them in a robotic lab, and learn from experimental feedback. Applied to glycoside hydrolases, the agents discovered enzymes with substantially altered substrate specificity toward non-native sugars and progressively learned the structure of the underlying sequence space.

Related event: Autonomous AI Agents Design High-Activity Enzymes in Closed-Loop Lab(2 posts)→

Original post →

More from Research

Research channel →