Xue Qin

Forget retraining your robot from scratch: this capability-centric approach lets embodied agents learn new tricks without losing their core identity or safety guarantees.

Guaranteeing safe and reliable behavior in embodied agents requires external runtime governance, not just smarter agents.

Naive upgrades of embodied agent capabilities lead to unsafe activations in 60% of cases, but a governed upgrade framework can maintain task success while ensuring zero unsafe activations.