What are Information Agents?

An information agent is a computational software entity (an intelligent agent) that may access one or multiple, distributed, and heterogeneous information sources available, and pro-actively acquires, mediates, and maintains relevant information on behalf of its user(s) or other agents preferably just-in-time. In other words, information agents are supposed to cope with the difficulties associated with the information overload of the user. This implies their ability to semantically broker information by:

(1) providing a pro-active resource discovery;
(2) resolving the information impedance of information consumers and providers;
(3) offering value-added information services and products to the user or other agents.

Intelligent information agents may be classified according to one or more of the following features:

- Non-cooperative or cooperative information agents, depending on the ability if the agents cooperate with each other for the execution of their tasks. Several protocols and methods are available for achieving cooperation among autonomous information agents in different scenarios, like hierarchical task delegation, contracting, and decentralized negotiation.

- Adaptive information agents are able to adapt themselves to changes in networks and information environments. Examples of such agents are learning personal assistants on the Web.

- Rational information agents behave utilitarian in an economic sense. They are acting, and may even collaborate together, to increase their own benefits. The main application domains of such kinds of agents are automated trading and electronic commerce in the Internet. Examples include the variety of shop bots, and systems for agent-mediated auctions on the Web.

- Mobile information agents are able to travel autonomously through the Internet. Such agents enable, dynamic load balancing in large-scale networks, reduction of data transfer among information servers, and migration of small business logic within medium-range corporate intranets on demand.

Regarding the basic skills of information agents we can differentiate between communication, knowledge, collaboration, and rather low-level task skills.

Communication skills of an information agent include either communication with information systems and databases, human users, or other agents. In the latter case, the use of a commonly agreed agent communication language (ACL) such as FIPA ACL and KQML has to be considered on top of, for example, middleware platforms or specific APIs. Representating and processing ontological knowledge and metadata, profiles and natural language input, translation of data formats as well as the application of machine learning techniques, enable an information agent to acquire and maintain knowledge about itself and its environment. High-level collaboration with other agents can rely, for example, on suitable coordination techniques such as service brokering, matchmaking, negotiation, and collaborative (social) filtering, whereas collaborating with human users mainly corresponds to the application of techniques stemming from the domain of human-agent interaction (HAI) and affective computing (AC).



Literature:

1.M. Klusch (ed.): Intelligent Information Agents. Springer Verlag, 1999.

2.M. Klusch: Information Agent Technology for the Internet: A Survey. Journal Data & Knowledge Engineering, Elsevier Science, 36(3), 2000.

3.M. Klusch (ed.) Special issue on Intelligent Information Agents: Theory and Applications, Intelligent Cooperative Information Systems, vol. 10(1&2), March 2001.