Integrating agent-based mixed-initiative control with an existing multi-agent planning system

Explores the impact of the role(s) that people play in large-scale multi-agent systems. We must develop strategies for coordinating not only the problem-solving behavior of autonomous agent communities, but also their information sharing and mixed-initiative human interaction behavior. In this paper, we describe our experience with combining two interactive agent systems: TRIPS (The Rochester Interactive Planning System) and CAMPS-MP (Constraint-based Airlift Mission Planning Scheduler-Mission Planner), an interactive airlift scheduling tool developed for the US Air Force. This revealed requirements for effective multi-agent mixed-initiative interactions, including the role of explanation and the need for contextual information sharing among the agents