In this paper, we outline a framework for the development of natural language interfaces to agent systems with a focus on action representation. The architecture comprises a natural language parser and a case frame based analysis for the semantic representation of the linguistic content of the input. The knowledge base is the core component of the system used in the mapping and interpretation process. It features a representation of actions and related objects in a conceptual hierarchy, which is tailored to provide a connection between the natural language interface and the artificial agent’s action repertoire. The crucial issue is the development of a representation formalism for actions, which is specifically suited to link linguistic inputs of the human user to action sets of artificial agents. The framework has been employed in the development of various agent systems and their natural language interfaces, including simulated household robots, an interior design system, a travel...