Safety Beyond Verification: The Need for Continual, User-Driven Assessment of AI Systems

Siddharth Srivastava, Georgios Fainekos, Pulkit Verma, Daniel Bramblett

Published in IJCAI Workshop on User-Aligned Assessment of Adaptive AI Systems, 2025

Examines the existing researching on assessing the safety and functionality of taskable AI systems that are designed to continually learn and solving user-desired tasks in user-specific environments.