Agent interoperation across multiagent system boundaries

Abstract

Recently the number of autonomous agents and multiagent systems (MAS) that have been developed by different developers has increased. Despite efforts for the creation of standards (eg. in communication languages, registration protocols etc.), it is clear that at least in the near term heterogeneous agents and MASs will be prevalent. Therefore, mechanisms that allow agents and/or MASs to interoperate and transact are needed. In this paper we report on a case study and lessons learned of an interoperator agent we developed. We discuss requirements for interoperation mechanisms, resulting challenges and our design decisions and implementation of the RETSINA-OAA InterOperator 1.

Topologies of agents interactions in knowledge intensive multi-agent systems for networked information services

“…Some of the previous work in multi-agent system development concentrated on domain-independent frameworks, standard protocol definitions, some handling of uncertainty and utility, and extensive models of collaboration [16]. However, there lacks methods for solid decision-theoretic model of agents learning, adaptation, control and collaboration.…”

“…However, a static distribution of agents is very unlikely to exist. For dynamic multi-agent systems, agents need to know how and where to find the other agents [16]. The dynamic nature of agent distribution motivates this research to look at the topological models of MAS and study how these models facilitate or hurdle the agent collaborations [10].…”

Adaptive Medical Workflow Management for a Context-Dependent Home Healthcare Assistance Service

“…BDI agents have been applied in rather different application domains, such as softbots, Web-based information systems, and robotics; e.g., see [8,12].…”

The Cobasa Architecture as an Answer to Shop Floor Agility

“…The notion of brokers, also known as middle agents, match makers, facilitators, and mediators is a subject of intense research in the multiagents field (Giampapa et al 2000;Klusch and Sycara 2001;Payne et al 2002;Sycara et al 1997;Wiederhold 1992;Wong and Sycara 2000). The broker therefore interacts with the human, the cluster, and the candidate members to the consortium.…”