8.6.1 Agent development is shifting from a centralised agent system to collaborative multiagent systems. A network of collaborating solver agents is one in which each agent deals with a one sub-problem. Mediator agents "match" the solutions of the solver agents. For instance, the Globus project, of Argonne National Laboratory and the University of Southern California's Information Science Institute, provides basic software infrastructure for computations that integrate geographically disparate resources. [2] The Infospheres project at Caltech provides a distributed programming layer using the Web, Java and the Internet for the purposes of delivering education materials that are customisable for specific classes. They condense their goals in three: Intensity (higher levels of engagement); Simulation (immediate ability to practice with consequences); and Collaboration (multi-learner and real-time access to expertise knowledge). [3]

8.6.2 Software agents, both independently and through their interaction with multiagent systems, are transforming the Internet's already multifaceted character. Functioning through the medium of autonomous actions, agents and agent systems move onto the net's distributed, large-scale, dynamic structure on behalf of often anonymous servers and human users scattered around the globe. Their purpose is to create open, flexible systems that shape future communities, commerce, and knowledge exchange. Agents linked to the electric power grid create networked "smart homes" [4] and shift virtual communities by creating surrogates and aliases for people and change business and manufacturing processes. [top]