Int. J. Intelligent Systems Technologies and Applications, Vol. 9, No. 1, 2010 49 Copyright © 2010 Inderscience Enterprises Ltd. Personalised distributed information retrieval-based agents Samir Kechid* and Habiba Drias Faculty of Electrical and Computer Science, Research Laboratory in Artificial Intelligence (LRIA), Department of Computer Science, USTHB, El Alia BP 32, Bab Ezzouar 16111, Algiers E-mail: kechidsam@yahoo.fr E-mail: skechid@usthb.dz E-mail: h_drias@hotmail.fr E-mail: hdrias@usthb.dz *Corresponding author Abstract: This paper proposes a new approach using a multi-agents system for personalising the distributed information retrieval (DIR). Most prior research in DIR focused on selecting and merging information that has the most relevant content according to the query, but ignored the user’s specific needs. Our approach extends the state-of-the-art in a DIR. Firstly, it develops an agent called user-agent for managing the user profile. Secondly, it develops an agent called source-agent for each information source in order to manage its information source. Finally, it develops an agent called agent-broker for cooperating between user-agent and each source-agent in order to select the best source and merge their best documents in response to the user’s query. The approach has been experimented with several known information sources. The experimental results show that the approach: (1) improve the relevance of the result, (2) reduce the response times and (3) improve the system extensibility. Keywords: distributed information retrieval; mutli-agents systems; user profile; source profile; source selection; result merging. Reference to this paper should be made as follows: Kechid, S. and Drias, H. (2010) ‘Personalised distributed information retrieval-based agents’, Int. J. Intelligent Systems Technologies and Applications, Vol. 9, No. 1, pp.49–74. Biographical notes: Samir Kechid is a Teacher of Computer Science and Software Engineering at Algiers University of Science and Technology U.S.T.H.B. He has received Magister in Computer Science and Software Engineering in U.S.T.H.B in 2002 and the PhD in Computer Science from the same university in 2009. His research interests include multi-agents systems, e-business, information retrieval and user profiling. Habiba Drias holds the Master degree in Computer Science from Case Western Reserve University, Cleveland, OH, USA (1984) and the Doctorate degree prepared in Collaboration with Paris University from Algiers USTHB University (1993). She has directed the Computer Science Institute of USTHB and then the Algerian National Institute of Informatics – INI. She has over a hundred published papers in the domain of artificial intelligence,