Research on resource-bounded agents has established that rational agents need to be able to revise their commitments in the light of new opportunities. In the context of collaborative activities, rational agents must be able to reconcile their intentions to do team-related actions with other

The original formulation of SharedPlans by B. Grosz and C. Sidner ( 1990) was developed to provide a model of collaborative planning in which it was not necessary for one agent to have intentions-to toward an act of a different agent. Unlike other contemporaneous approaches (J.R. Searle, 1990

was originally conceived to address. Thus we can conjecture that the incorporation of autonomic principles into the design of Multi-Agent Systems is indeed a desirable objective. As an illustration of how this may be achieved, a strategy termed Collaborative Agent Tuning is described, which seeks to optimise

Collaborative agent-based learning with limited data exchange.

Psychological studies on teamwork have shown that an effective team often can anticipate information needs of teammates based on a shared mental model. Existing multi-agent models for teamwork are limited in their ability to support proactive information exchange among teammates. To address

situation awareness, resource distribution and load balancing, etc. This paper presents an agent-based approach to designing intelligent team training systems. We envision a computer-based training system in which teams are trained by putting them through scenarios, which allow them to practice

amounts of data and information that threaten to overload commanders and staff. Needed are integrated approaches that will improve collection, analysis, exchange and presentation of timely information tailored to specific users, allowing each an accurate view of the battlespace. Software agent

We describe a cognitive model of a collaborative agent that can serve as the basis for automated systems that must collaborate with other agents, including humans, to solve problems. This model builds on standard approaches to cognitive architecture and intelligent agency, as well as formal models

twork. The Impact server provides the infrastructure upon which different Impact agents can interact. To avoid a performance bottleneck, multiple copies of the server can be replicated and scattered across the network. Impact agents A set of data objects can be represented in a wide variety of ways

certain benefits, almost invariably aggravate these difficul-ties. Hence, the optimal usage of the limited computational resources is essential if the application is to perform ad-equately and meet end-user requirements. One approach to optimising resource usage concerns Collaborative Agent Tuning (CAT