Genetic Programming (GP) is a technique that can be used to automatically program computers to perform some required task. The technique is a kind of genetic algorithm in which the representation is a program tree instead of a bit-string and the fitness of each tree is evaluated by executing the computer program that it represents. The subject of this thesis is to investigate the use of GP to automatically program multiagent systems. To achieve this goal, we consider the general problems in creating multiagent systems, and show how GP can be used to provide solutions to many of them. Our key contributions are as follows: We show that it is possible to evolve multiagent systems using GP that: exhibit coordinated, coherent behaviour communicate explicitly, and in doing so decide what to communicate and how can resolve conflicts can be integrated into an existing society of agents. We also consider the technical scalability issues involved in the use of GP, both generally and in particular as a technique for automatically programming agents, and propose some solutions to these problems.