Abstract
The formation of longitudinal queues is critical for biological and artificial swarm systems to achieve efficient long-distance navigation. However, the "black-box" nature of conventional deep reinforcement learning models often obscures the microscopic rules driving the emergence of such ordered behaviors. To address this challenge, this paper proposes an interpretable computational model of collective behavior based on Projective Simulation and Episodic Compositional Memory, which enables individuals to learn decision-making strategies within a transparent state-action network. Simulation results demonstrate that the swarm can self-organize into stable and highly elongated longitudinal queues. Crucially, through visualization of microscopic strategies, we reveal a deterministic target-priority mechanism: when local neighbor alignment conflicts with global target orientation, individuals learn to strictly prioritize the target direction, serving as the key driving force for queue formation. Further parametric analysis indicates that the action space granularity exerts a nonlinear impact on stability, identifying moderate control precision as the optimal choice. This study not only provides a transparent computational explanation for the self-organization mechanism of queues in collective motion but also offers a theoretical foundation for designing interpretable swarm navigation systems.