Modeling Goal Alignment in Human-AI Teaming: A Dynamic Game Theory Approach

Abstract

As human-AI teaming becomes increasingly prevalent, goal alignment has emerged as a critical yet unsolved issue. Misaligned goals can be amplified by the situation and strategic interactions, which can further impact the teaming process and performance. These interrelated factors lack a systematic and computational model. To address this gap, we developed a dynamic game theoretical framework simulating the human-AI interdependency by integrating the Drift Diffusion Model simulating the goal alignment process. A 3 (Situation Structure) x 3 (Strategic Behaviors) x 2 (Initial Goal Alignment) simulation study of human-AI teaming was designed. Results showed that teaming with an altruistic agent in a competitive situation leads to the highest team performance. Moreover, goal alignment process can dissolve the initial goal conflict. Our study provides a first step of modeling goal alignment and implies a tradeoff between a balanced and cooperative team to guide human-AI teaming design.