With the rapid development of urbanization, the problem of urban traffic congestion has become increasingly prominent. Dynamic route guidance promises to improve the capacity of urban traffic management and mitigate traffic congestion in big cities. In the design of simulation-based experiments for most dynamic route guidance methods, the simulation data is generally estimated from a specific traffic scenario in the real-world. However, highly dynamic traffic in the city implies that traffic scenarios in real systems are diverse. Therefore, if a route guidance method cannot adjust its strategy according to the spatial and temporal characteristics of different traffic scenarios, then it cannot guarantee optimal results under all traffic scenarios. Thus, ideal dynamic route guidance methods should have a highly adaptive learning ability under diverse traffic scenarios so as to have extensive improvement capabilities for different traffic scenarios. In this study, an A* trajectory rejection method based on multi-agent reinforcement learning (A*R²) is proposed; the method integrates both system and user perspectives to mitigate traffic congestion and reduce travel time (TT) and travel distance (TD). First, owing to its adaptive learning ability, the A*R² can comprehensively analyze the traffic conditions for different traffic scenarios and intelligently evaluate the road congestion index from a system perspective. Then, the A*R² determines the routes for all vehicles from user perspective according to the road network congestion index. An extensive set of simulation experiments reveal that, under various traffic scenarios, the A*R² can rely on its adaptive learning ability to achieve better traffic efficiency. Moreover, even in cases where many drivers are not fully compliant with the route guidance, the traffic efficiency can still be improved significantly by A*R².