Workshop on Evaluation of Interactive Agents

This workshop examines evaluation for agents whose success depends on sustained interaction. Researchers discuss understanding user goals, maintaining context, using tools, recovering from errors and collaborating across extended task trajectories in settings such as research, education and software development. Session: 08:00–17:00 (America/New_York). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.