Planning and reflection in autonomous agents

In 1985 the author began a two year ESRC funded project to look at the interpretation and generation of cooperative dialogue between agents. The idea was to derive discourse from an underlying planning system-the belief was that the fundamental driving force behind dialogue is the problem solving ability of the agent. The research showed, via the construction of a number of computational models, that flexible dialogue could be obtained under this organisation. However, a number of important lessons emerged about the nature and character of effective agent architectures. These are being followed up, in particular, the role of reflection and planning in agent architectures is being investigated