Abstract
This paper describes a synthesis of two well-known agent paradigms: Agent-Oriented Programming, Shoham (1990), and the Knowledge Query & Manipulation Language, Finin (1993). The initial implementation of AOP, Agent-0, is a simple language for specifying agent behaviour. KQML provides a standard language for inter-agent communication. Our integration (which we have called Agent-K) demonstrates that Agent-0 and KQML are highly compatible. Agent-K provides the possibility of inter-operable (or open) software agents, that can communicate via KQML and which are programmed using the AOP approach. We begin with an overview of AOP and KQML before going on to describe our motivations for this work. This is followed by a description of the design and implementation of Agent-K. We conclude with a discussion of the issues raised by the integration of AOP and KQML.
Original language | English |
---|---|
Pages | 1-16 |
Number of pages | 16 |
Publication status | Published - 1994 |
Event | CIKM Workshop on Intelligent Information Agents - Gaithersburg, United States Duration: 2 Dec 1994 → 2 Dec 1994 |
Workshop
Workshop | CIKM Workshop on Intelligent Information Agents |
---|---|
Country/Territory | United States |
City | Gaithersburg |
Period | 2/12/94 → 2/12/94 |
Bibliographical note
The work described here is supported by the UK Engineering and Physical Science Research Council (EPSRC). We wish to acknowledge the assistance of Yoav Shoham, Tim Finin, Jay Weber, Becky Thomas and David Galles for various helpful comments and for providing the original Agent-0 and KAPI code. Thanks also to Ciara Byrne and Bob Holton for comments on an earlier draft of this documentKeywords
- software agents
- agent-oriented programming
- communication