Artificially intelligent agents increasingly collaborate with humans in human-agent teams. Timely proactive sharing of relevant information within the team contributes to the overall team performance. This paper presents a machine learning approach to proactive communication in AI-agents using contextual factors. Proactive communication was learned in two consecutive experimental steps: (a) multi-agent team simulations to learn effective communicative behaviors, and (b) human-agent team experiments to refine communication suitable for a human team member. Results consist of proactive communication policies for communicating both beliefs and goals within human-agent teams. Agents learned to use minimal communication to improve team performance in simulation, while they learned more specific socially desirable behaviors in the human-agent team experiment
DOCUMENT
With artificial intelligence (AI) systems entering our working and leisure environments with increasing adaptation and learning capabilities, new opportunities arise for developing hybrid (human-AI) intelligence (HI) systems, comprising new ways of collaboration. However, there is not yet a structured way of specifying design solutions of collaboration for hybrid intelligence (HI) systems and there is a lack of best practices shared across application domains. We address this gap by investigating the generalization of specific design solutions into design patterns that can be shared and applied in different contexts. We present a human-centered bottom-up approach for the specification of design solutions and their abstraction into team design patterns. We apply the proposed approach for 4 concrete HI use cases and show the successful extraction of team design patterns that are generalizable, providing re-usable design components across various domains. This work advances previous research on team design patterns and designing applications of HI systems.
MULTIFILE
Organizing entrepreneurial collaboration in small, self-directed teams is gaining popularity. The underlying co-creation processes of developing a shared team vision were analyzed with a core focus on three underlying processes that originate from the shared mental models framework. These processes are: 1) the emergence of individual visions and vision integration, 2) conflict solving, and 3) redesigning the emerging knowledge structure. Key in the analysis is the impact of these three processes on two outcome variables: 1)the perceived strength of the co-creation process, 2) the final team vision. The influence of business expertise and the relationship between personality traits and intellectual synergy was also studied. The impact of the three quality shared mental model (SMM) variables proves to be significant and strong, but indirect. To be effective, individual visions need to be debated during a second conflict phase. Subsequently, redesigning the shared knowledge structure resulting from the conflict solving phase is a key process in a third elaboration phase. This sequence positively influences the experienced strength of the co-creation process, the latter directly enhancing the quality of the final team vision. The indirect effect reveals that in order to be effective, the three SMM processes need to be combined, and that the influence follows a specific path. Furthermore, higher averages as well as a diversity of business expertise enhance the quality of the final team vision. Significant relationships between personality and an intellectual synergy were found. The results offer applicable insights for team learning and group dynamics in developing an entrepreneurial team vision. LinkedIn: https://www.linkedin.com/in/rainer-hensel-phd-8ba44a43/ https://www.linkedin.com/in/ronald-visser-4591034/
DOCUMENT
