Teaming up with information agents
This work addresses human-machine teaming for information agents, which is incremental as it extends existing research from physical to information domains.
The paper tackles the problem of designing AI systems to collaborate with humans as information agents, proposing team design patterns and testing them with a Collaborative Intelligence Analysis tool.
Despite the intricacies involved in designing a computer as a teampartner, we can observe patterns in team behavior which allow us to describe at a general level how AI systems are to collaborate with humans. Whereas most work on human-machine teaming has focused on physical agents (e.g. robotic systems), our aim is to study how humans can collaborate with information agents. We propose some appropriate team design patterns, and test them using our Collaborative Intelligence Analysis (CIA) tool.