Autonomousagentsandmulti-agentsystemsarecomputationalsystemsinwhich several (semi-)autonomous agents interact with each other or work together to performsomesetoftasksorsatisfysomesetofgoals.Thesesystemsmayinvolve computational agents that are homogeneous or heterogeneous,they may involve activities on the part of agents having common or distinct goals, and they may involve participation on the part of humans and intelligent agents. ThisvolumecontainsselectedpapersfromPRIMA2004,the 7thPaci?cRim InternationalWorkshoponMulti-agents,heldinAuckland,NewZealand,during August8-13,2004in conjunctionwith the8thPaci?cRim InternationalConf- ence on Arti?cial Intelligence (PRICAI 2004). PRIMA is a series of workshops on autonomous agents and multi-agents that focusses on the research activities in the Asian and Paci?c Rim countries. PRIMA 2004 was built upon the great successes of its predecessors. Fifty-two papers were submitted to the workshop, each paper was reviewed by three internationally renowned program committee members. After careful review, 24 papers were selected for this volume. We would like to thank all the authors who submitted papers to the workshop. We would also like to thank all the program committee members for their diligent work in reviewing the papers.Wewouldliketothankourinvitedspeakers,SandipSenandToruIshida. Additionally, we thank the editorial sta? of Springer for publishing this volume in the series Lecture Notes in Arti?cial Intelligence. Lastly, we want to thank our sponsors, the Auckland University of Technology's Knowledge Engineering and Discovery Research Institute (KEDRI), and the University of Auckland's Department of Computer Science, for the ?nancial support provided.