Existing models of plan inference (PI) in conversation have assumed that the agent whose plan is being inferred (the actor) and the agent drawing the inference (the observer) have identical beliefs about actions in the domain. I argue that this assumption often results in failure of both the PI process and the communicative process that PI is meant to support. In particular, it precludes the principled generation of appropriate responses to queries that arise from invalid plans. I describe a model of PI that abandons this assumption. It rests on an analysis of plans as mental phenomena. Judgments that a plan is invalid are associated with particular discrepancies between the beliefs that the observer herself holds. I show that the content of an appropriate response to a query is affected by the types of any such discrepancies of belief judged to be present in the plan inferred to underlie that query. The PI model described here has been implemented in SPIRIT, a small demonstration system that answers questions about the domain of computer mail.
