TL;DR: Several problematic issues and potential solutions are discussed, including representational challenges in advertising complex databases, the need for persistent requests in information brokering, the dilemm~ between explicit vs. implicit broKQML, problems in error recovery and response timing, consistency among information providers, and efficiency.
Abstract: As agents see more use as entry points to incxeasingly complex distributed information networks, agent communication technologies such as the Knowledge Query and Manipulation Language and the SHADE Matchmaker will play an important role. We describe our experiences with these technologies as applied to two applications: collaborative engineering and satellite image retrieval. Based on these experiences, we outline the major observed benefits of KQML and matchmaking. In addition, we discuss several problematic issues and potential solutions, including representational challenges in advertising complex databases, the need for persistent requests in information brokering, the dilemm~ between explicit vs. implicit brokering, problems in error recovery and response timing, consistency among information providers, and efficiency.
TL;DR: KQML is described and evaluated as an agent communication language relative to the desiderata, which are divided into seven categories: form, content, semantics, implementation, networking, environment, and reliability.
Abstract: This paper offers some opinions on the desirable features of languages and protocols for communication among intelligent information agents. These desiderata are divided into seven categories: form, content, semantics, implementation, networking, environment, and reliability. The Knowledge Query and Manipulation Language (KQML), is a new language and protocol for exchanging information and knowledge. This work is part of a larger effort, the ARPA Knowledge Sharing Effort, which is aimed at developing techniques and methodologies for building largescale knowledge bases which are sharable and reusable. KQML is both a message format and a message-handling protocol to support run-time knowledge sharing among agents. KQML is described and evaluated as an agent communication language relative to the desiderata.
TL;DR: The Aide de Camp project at the University of Liverpool has been addressing the problem of information overload (together with related issues), particularly with regard to electronic mail, and utilises a system of cooperating knowledge-based systems which reduces the overall number of messages for the organisation.
Abstract: The Aide de Camp project at the University of Liverpool has been addressing the problem of information overload (together with related issues), particularly with regard to electronic mail. One successful application supplied users with a knowledge-based system (KBS) which, together with a sophisticated e-mail user agent, can handle routine communications on behalf of the user. This approach was used to create a software knowledge-based assistant (KBA) which helps a lecturer in the administration of an undergraduate course. Whilst this approach is successful in its objective of reducing the number of messages presented to the lecturer, it often achieves this by increasing the number of messages other members of the organisation receive (for example the student and the technical support staff). To overcome this failing, the work utilises a system of cooperating knowledge-based systems which reduces the overall number of messages for the organisation. This cooperation is implemented using the Knowledge Query and Manipulation Language (KQML), which provides a protocol for KBS's to share and exchange knowledge.
TL;DR: This chapter discusses the desirable features of languages and protocols for communication among intelligent information agents and KQML is described and evaluated as an agent communication language relative to the desiderata.
Abstract: This chapter discusses the desirable features of languages and protocols for communication among intelligent information agents. These desiderata are divided into seven categories: form, content, semantics, implementation, networking, environment, and reliability. The Knowledge Query and Manipulation Language (KQML) is a new language and protocol for exchanging information and knowledge. This work is part of a larger effort, the ARPA Knowledge Sharing Effort, which is aimed at developing techniques and methodologies for building large-scale knowledge bases that are sharable and reusable. KQML is both a message format and a message-handling protocol to support run-time knowledge sharing among agents. KQML is described and evaluated as an agent communication language relative to the desiderata.