Abstract: Although current land-use and land-cover change(LUCC) and urban growth simulation models can simulate and predict spatial pattern of farmland, it’s not applicable for the interpretation of interaction between all kinds of agents during the process of farmland conversion and reasonable spatio-temporal simulation and planning of farmland conversion. Following the principles of maximal spatial and temporal planning efficiency as well as sustainable development, a spatio-temporal simulation and planning model for farmland conversion is developed with integration of multi-agent system and resource economics theory. The proposed model, which consists of some related components, i.e., external environment, multi-agent system, decision-making framework, can explicitly represent agents’ spatio-temporal decision-making behaviors and rules during the process of farmland conversion, simulate the developmental tendency of farmland conversion under different planning guidelines and provide auxiliary decision-making support for farmland resources planning. The proposed model is applied to the simulation and planning of farmland conversion in the core areas of Changsha, Zhuzhou, Xiangttan city cluster in 2006-2020, which is the national comprehensive reforms test areas of building resource-saving and environment-friendliness society in China. The simulation results and the analysis of ecosystem service loss under different planning guidelines show that the model is able to provide a spatial exploratory tool for spatio-temporal planning of farmland conversion.