Stanford SAIL unveils DexAgent from a single human video
According to the Stanford AI Lab blog, DexAgent converts a single egocentric human video into robot training data via an agentic framework with a self-evolving tool library for dexterous manipulation.
SourceAnalysis
Stanford AI Lab announced on October 14, 2026 that its new DexAgent framework can turn a single egocentric human video into robot training data for dexterous manipulation tasks.
The agentic system relies on a self-evolving tool library to generate the necessary training signals according to the Stanford AI Lab announcement.
Stanford AI Lab
@StanfordAILabThe Stanford Artificial Intelligence Laboratory (SAIL), a leading #AI lab since 1963.