The Role of Conversation Policy in Carrying Out Agent Conversations

Structured conversation diagrams, or conversation specifications, allow agents to have predictable interactions and achieve predefined information-based goals, but they lack the flexibility needed to function robustly in an unpredictable environment. We propose a mechanism that combines a typical conversation structure with a separately established policy to generate an actual conversation. The word ''policy'' connotes a high-level direction external to a specific planned interaction with the environment. Policies, which describe acceptable procedures and influence decisions, can be applied to broad sets of activity. Based on their observation of issues related to a policy, agents may dynamically adjust their communication patterns. The policy object describes limitations, constraints, and requirements that may affect the conversation in certain circumstances. Using this new mechanism of interaction simplifies the description of individual conversations and allows domain-specific issues to be brought to bear more easily during agent communication. By following the behavior of the conversation specification when possible and deferring to the policy to derive behavior in exceptional circumstances, an agent is able to function predictably under normal situations and still act rationally in abnormal situations. Different conversation policies applied to a given conversation specification can change the nature of the interaction without changing the specification