1995 · 212 citations · 6 references
ComputingComputer ScienceSystems EngineeringDistributed SystemsKnowledge RepresentationKnowledge SharingCoordination MechanismsDistributed CoordinationIntelligent AgentsMulti-agent SystemsAgent CoordinationCommunication ProtocolsConversational AgentsCoordinationCoordination LanguagesCoordination ProtocolsEnterprise IntegrationN-queens Problem
Agent interaction occurs at multiple levels, and prior work has addressed the information content level with KIF and the intentional level with KQML. This paper introduces COOL, a coordination language that uses speech‑act communication within a structured conversation framework to capture agents’ coordination mechanisms. COOL is applied to model supply‑chain coordination in manufacturing enterprises and to design and validate coordination protocols, and its core elements include conversation objects, rules, error‑recovery, continuation, and nesting. The paper provides COOL source code and a running n‑queens trace in the appendix. Topic areas: Coordination, Intelligent agents in enterprise integration.
Agent interaction takes place at several levels. Current work in the ARPA Knowledge Sharing Effort has addressed the information content level by the KIF language and the intentional level by the KQML language. In this paper we address the coordination level by means of our Coordination Language (COOL) that relies on speech act based communication, but integrates it in a structured conversation framework that captures the coordination mechanisms agents use when working together. We are currently using this language (i) to represent coordination mechanisms for the supply chain of manufacturing enterprises modeled as intelligent agents and (ii) as an environment for designing and validating coordination protocols for multi-agent systems. This paper describes the basic elements of this language: conversation objects, conversation rules, error recovery rules, continuation rules, conversation nesting. The actual COOL source code and a running trace for the n-queens problem are presented in the Appendix. Topic areas: Coordination, Intelligent agents in enterprise integration
6