An often quoted model integrating GIS and Agent-based modelling is that by Randy Gimblett et al. Their agent-based model, RBSim used real-world geographic features (including topography, vegetation and roads) to evaluate the recreational use of
The model itself is quite simple but highlights how geographic data can be integregated into an agent-based model. Additionally how agent-based modelling can be used as a tool to 'think with' by allowing the user to alter the setup model parameters (eg the number of hikers).
Further details about the model can be seen on the project website or the model can be downloaded by clicking here.
Good articles describing the model can be seen in:
Gimblett, H.R., Richards, M.T. and Itami, R.M. (2002), 'SImulating Wildland Recreation Use and Conflicting Spatial Interactions using Rule-Driven Intelligent Agents', in Gimblett, H.R. (ed.) Integrating Geographic Information Systems and Agent-Based Modelling Techniques for Simulating Social and Ecological Processes, Oxford University Press, Oxford, pp. 211-243.
Itami, R.M. (2002), 'Mobile Agents with Spatial Intelligence', in Gimblett, H.R. (ed.) Integrating Geographical Information Systems and Agent-Based technologies for modelling and simulating social and ecological phenomena, Oxford University Press, Oxford, pp. 191-210.