91

RésuméIn this paper we present a multi-agent system for searching the Internet. The search for interesting documents on the Internet is becoming increasingly difficult, mainly because search engines cannot cope with the expansion of the Internet. Consequently, the results of queries are often of very poor quality. Multi-agent systems can give more accurate results than traditional search engines because agents can be specialized in different tasks (search or filtering) and can personalize information. We implemented such an approach using an open multi-agent system containing personal assistants, library agents, filter agents and search agents. In this paper, we detail the elements of our multi-agent system and compare its performance with more traditional search engines. Our results yield a better accuracy.