The Third Workshop on Agents in the Wild: Safety, Security, and Beyond

The workshop examines safety and security when autonomous agents operate with tools and persistent memory. Invited and contributed work considers emerging failure modes, adversarial interactions and the challenges of evaluating systems whose behaviour unfolds through extended real-world activity. Session: 08:00–17:00 (Australia/Sydney). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.