Artificial Society is an analytical foundation of various complex eco- and social systems. Such system is usually implemented via multiagent approach. However, there is no consensus on how to model the agent's decision-making process,since different application scenarios concentrate on different facets. This, to some extent, hinders model reuse and system integration. This paper proposes a general cognitive architecture that attempts to adapt all the aspects of agent's decision-making in artificial societies, so that different programs and software can be reorganized and integrated conveniently. To illustrate its implementation, two simulations-emergent evacuation and population evolution-are conducted. These tests clearly show that the proposed architecture is able to support different agent-based models. Problems that might be encountered, as well as possible strategies, are also proposed in the end.