Asymmetric interaction preference induces cooperation in human-agent hybrid game

With the advancement of artificial intelligence, human interest in human-agent collaboration has grown, raising a series of challenges regarding the relationship between agents and humans, such as trust and cooperation. This leads to the inevitable consideration of the inherent human traits of subjective interaction preferences for different groups, particularly in human-agent hybrid systems where human-human, agent-agent, and human-agent interactions coexist. However, understanding how individual interaction preferences influence cooperation within such systems remains a major challenge. To address this, this study proposes a human-agent hybrid prisoner’s dilemma game system within the framework of evolutionary game theory. In spatial networks, the primary distinction between agents and humans lies in their decision-making flexibility: humans possess higher adaptive capabilities, follow link dynamics, and employ free decision-making rules, which allows them to select different strategies for different neighbors. In contrast, agents follow node dynamics, applying uniform decision rules and using the same strategy across all neighbors. We define subjective preferences for individuals in various groups, including interaction preferences between homogeneous and heterogeneous groups. The simulation results demonstrate that both humans and agents display asymmetric interaction preferences toward groups with different identities, which significantly enhances cooperative behavior in the system. In the hybrid system, human groups exhibit more stable prosocial behavior, whereas agent groups form highly cooperative clusters when there is a strong interaction preference for human groups. Additionally, endowing agents with the ability to identify their opponents effectively mitigates the interaction dilemma among agents.