Self-Evolving Diversity-Driven Search for Robust AI Systems

The workshop studies diversity-driven search for discovering failures in interactive AI. It connects evolutionary computation, multi-objective optimization and adversarial evaluation, examining how to describe and explore safety scenarios across languages, modalities, tools, users and extended interaction sequences. Session: 08:00–17:00 (Australia/Sydney). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.