Recently, the study of intelligenceemerged from interactionsamong many agentshasbeenpopular. Inthisstudyitisrecognizedthatanetworkstructure oftheagentsplaysanimportantrole. Thecurrentstate-of-theartinage- based modeling tends to be a mass of agents that have a series of states thattheycanexpressasaresultofthenetworkstructureinwhichtheyare embedded. Agentinteractionsofallkindsareusuallystructuredwithcomplex networks. Researchoncomplexnetworksfocusesonscale-freenessofvarious kindofnetworks. Computationalmodelingofdynamicagentinteractionsonrichlystr- turednetworksisimportantforunderstandingthesometimescounter-intuitive dynamicsofsuchlooselycoupledsystemsofinteractions. Yetourtoolsto model, understand, andpredictdynamicagentinteractionsandtheirbe- vioroncomplexnetworkshavelaggedfarbehind. Evenrecentprogressin networkmodelinghasnotyeto?eredusanycapabilitytomodeldynamic processesamongagentswhointeractatallscalesonsuchassmall-worldand scale-freenetworks. Generallythehigh-dimensional, non-linearnatureofthe resultingnetwork-centricmulti-agentsystemsmakesthemdi?cultorimp- sibletoanalyzeusingtraditionalmethods. Agentsfollowlocalrulesunder complexnetworkconstraints. Theideaofcombiningmulti-agentsystemsand complexnetworksisalsoparticularlyrichandfreshtofostertheresearchon thestudyofverylarge-scalemulti-agentsystems. Weintendtoturnthisintoanengineeringmethodologytodesigncomplex agentnetworks. Multi-agentnetworkdynamicsinvolvesthestudyofmany agents, constituentcomponentsgenerallyactiveoneswithasimplestructures andwhosebehaviorisassumedtofollowlocalrules, andtheirinteractionson complexnetwork. Abasicmethodologyistospecifyhowtheagentsinteract, andthenobserveemergentintelligencethatoccuratthecollectivelevelin ordertodiscoverbasicprinciplesandkeymechanismsforunderstandingand shapingtheresultingintelligentbehavioronnetworkdynamics. Thevolumecontainsrefereedpapersaddressingvariousimportanttopics thataimsattheinvestigationofemergentintelligenceonnetworkedagents. vi Preface Especiallymostpapershighlightonthetopicssuch"networkformationamong agents," "in?uenceofnetworkstructuresonagents," "network-basedcoll- tivephenomenaandemergentintelligenceonnetworkedagents." TheselectedpapersofthisvolumewerepresentedattheWorkshopon EmergentIntelligenceofNetworkedAgents(WEIN06)attheFifthInt- nationalJointConferenceonAutonomousAgentsandMulti-agentSystems (AAMAS2006), whichwasheldatFutureUniversity, Hakodate, Japan, from May8to12,2006. WEIN06isconcernedwithemergenceofintelligentbe- viorsovernetworkedagents andfosteringtheformationofanactivemul- disciplinarycommunityonmulti-agentsystemsandcomplexnetworks. We especiallyintendedtoincreasetheawarenessofresearchersinthesetwo?elds sharingthecommonviewoncombiningagent-basedmodelingandcomplex networksinordertodevelopinsightandfosterpredictivemethodologiesin studyingemergentintelligenceonofnetworkedagents. Fromthebroadsp- trumofactivities, leadingexpertspresentedimportantpaperandnumerous practicalproblemsappearthroughoutthisbook. Weinvitedhighqualityc- tributionsonawidevarietyoftopicsrelevanttothewideresearchareasof multi-agentnetworkdynamics. Weespeciallycoveredin-depthofimportant areas including: Adaptation and evolution in complex networks, Economic agentsandcomplexnetworks, Emergenceincomplexnetworks, Emergent- telligenceinmulti-agentsystems, Collectiveintelligence, Learningandevo- tioninmulti-agentsystems, Webdynamicsascomplexnetworks, Multi-agent basedsupplynetworks, Network-centricagentsystems, Scalabilityinmul- agentsystems, Scale-freenetworks, Small-worldnetworks.

While the significance of networks in various human behavior and activities has a history as long as human's existence, network awareness is a recent scientific phenomenon. The neologism network science is just one or two decades old. Nevertheless, with this limited time, network thinking has substantially reshaped the recent development in economics, and almost all solutions to real-world problems involve the network element. This book integrates agent-based modeling and network science. It is divided into three parts, namely, foundations, primary dynamics on and of social networks, and applications. The authors begin with the network origin of agent-based models, known as cellular automata, and introduce a number of classic models, such as Schelling's segregation model and Axelrod's spatial game. The essence of the foundation part is the network-based agent-based models in which agents follow network-based decision rules. Under the influence of the substantial progress in network science in late 1990s, these models have been extended from using lattices into using small-world networks, scale-free networks, etc. The text also shows that the modern network science mainly driven by game-theorists and sociophysicists has inspired agent-based social scientists to develop alternative formation algorithms, known as agent-based social networks. It reviews a number of pioneering and representative models in this family. Upon the given foundation, the second part reviews three primary forms of network dynamics, such as diffusions, cascades, and influences. These primary dynamics are further extended and enriched by practical networks in goods-and-service markets, labor markets, and international trade. At the end, the book considers two challenging issues using agent-based models of networks: network risks and economic growth.

Artificial evolutionary systems are computer systems, inspired by ideas from natural evolution and related phenomena. The field has a long history, dating back to the earliest days of computer science, but it has only become an established scientific and engineering discipline since the 1990s, with packages for the commonest form, genetic algorithms, now widely available. Researchers in the Asia-Pacific region have participated strongly in the development of evolutionary systems, with a particular emphasis on the evolution of intelligent solutions to highly complex problems. The Asia-Pacific Symposia on Intelligent and Evolutionary Systems have been an important contributor to this growth in impact, since 1997 providing an annual forum for exchange and dissemination of ideas. Participants come primarily from East Asia and the Western Pacific, but contributions are welcomed from around the World. This volume features a selection of fourteen of the best papers from recent APSIES. They illustrate the breadth of research in the region, with applications ranging from business to medicine, from network optimization to the promotion of innovation.

Artificial evolutionary systems are computer systems, inspired by ideas from natural evolution and related phenomena. The field has a long history, dating back to the earliest days of computer science, but it has only become an established scientific and engineering discipline since the 1990s, with packages for the commonest form, genetic algorithms, now widely available. Researchers in the Asia-Pacific region have participated strongly in the development of evolutionary systems, with a particular emphasis on the evolution of intelligent solutions to highly complex problems. The Asia-Pacific Symposia on Intelligent and Evolutionary Systems have been an important contributor to this growth in impact, since 1997 providing an annual forum for exchange and dissemination of ideas. Participants come primarily from East Asia and the Western Pacific, but contributions are welcomed from around the World. This volume features a selection of fourteen of the best papers from recent APSIES. They illustrate the breadth of research in the region, with applications ranging from business to medicine, from network optimization to the promotion of innovation.

Recently, the study of intelligenceemerged from interactionsamong many agentshasbeenpopular. Inthisstudyitisrecognizedthatanetworkstructure oftheagentsplaysanimportantrole. Thecurrentstate-of-theartinage- based modeling tends to be a mass of agents that have a series of states thattheycanexpressasaresultofthenetworkstructureinwhichtheyare embedded. Agentinteractionsofallkindsareusuallystructuredwithcomplex networks. Researchoncomplexnetworksfocusesonscale-freenessofvarious kindofnetworks. Computationalmodelingofdynamicagentinteractionsonrichlystr- turednetworksisimportantforunderstandingthesometimescounter-intuitive dynamicsofsuchlooselycoupledsystemsofinteractions. Yetourtoolsto model, understand, andpredictdynamicagentinteractionsandtheirbe- vioroncomplexnetworkshavelaggedfarbehind. Evenrecentprogressin networkmodelinghasnotyeto?eredusanycapabilitytomodeldynamic processesamongagentswhointeractatallscalesonsuchassmall-worldand scale-freenetworks. Generallythehigh-dimensional, non-linearnatureofthe resultingnetwork-centricmulti-agentsystemsmakesthemdi?cultorimp- sibletoanalyzeusingtraditionalmethods. Agentsfollowlocalrulesunder complexnetworkconstraints. Theideaofcombiningmulti-agentsystemsand complexnetworksisalsoparticularlyrichandfreshtofostertheresearchon thestudyofverylarge-scalemulti-agentsystems. Weintendtoturnthisintoanengineeringmethodologytodesigncomplex agentnetworks. Multi-agentnetworkdynamicsinvolvesthestudyofmany agents, constituentcomponentsgenerallyactiveoneswithasimplestructures andwhosebehaviorisassumedtofollowlocalrules, andtheirinteractionson complexnetwork. Abasicmethodologyistospecifyhowtheagentsinteract, andthenobserveemergentintelligencethatoccuratthecollectivelevelin ordertodiscoverbasicprinciplesandkeymechanismsforunderstandingand shapingtheresultingintelligentbehavioronnetworkdynamics. Thevolumecontainsrefereedpapersaddressingvariousimportanttopics thataimsattheinvestigationofemergentintelligenceonnetworkedagents. vi Preface Especiallymostpapershighlightonthetopicssuch"networkformationamong agents," "in?uenceofnetworkstructuresonagents," "network-basedcoll- tivephenomenaandemergentintelligenceonnetworkedagents." TheselectedpapersofthisvolumewerepresentedattheWorkshopon EmergentIntelligenceofNetworkedAgents(WEIN06)attheFifthInt- nationalJointConferenceonAutonomousAgentsandMulti-agentSystems (AAMAS2006), whichwasheldatFutureUniversity, Hakodate, Japan, from May8to12,2006. WEIN06isconcernedwithemergenceofintelligentbe- viorsovernetworkedagents andfosteringtheformationofanactivemul- disciplinarycommunityonmulti-agentsystemsandcomplexnetworks. We especiallyintendedtoincreasetheawarenessofresearchersinthesetwo?elds sharingthecommonviewoncombiningagent-basedmodelingandcomplex networksinordertodevelopinsightandfosterpredictivemethodologiesin studyingemergentintelligenceonofnetworkedagents. Fromthebroadsp- trumofactivities, leadingexpertspresentedimportantpaperandnumerous practicalproblemsappearthroughoutthisbook. Weinvitedhighqualityc- tributionsonawidevarietyoftopicsrelevanttothewideresearchareasof multi-agentnetworkdynamics. Weespeciallycoveredin-depthofimportant areas including: Adaptation and evolution in complex networks, Economic agentsandcomplexnetworks, Emergenceincomplexnetworks, Emergent- telligenceinmulti-agentsystems, Collectiveintelligence, Learningandevo- tioninmulti-agentsystems, Webdynamicsascomplexnetworks, Multi-agent basedsupplynetworks, Network-centricagentsystems, Scalabilityinmul- agentsystems, Scale-freenetworks, Small-worldnetworks.

Understanding the mechanism of a socio-economic system requires more than an understanding of the individuals that comprise the system. It also requires understanding how individuals interact with each other, and how the agg- gated outcome can be more than the sum of individual behaviors. This book contains the papers fostering the formation of an active multi-disciplinary community on socio-economic systems with the exciting new ?elds of age- based modeling and econophysics. We especially intend to increase the awareness of researchers in many ?elds with sharing the common view many economic and social activities as collectives of a large-scale heterogeneous and interacting agents. Economists seek to understand not only how individuals behave but also how the interaction of many individuals leads to complex outcomes. Age- based modeling is a method for studying socio-economic systems exhibiting the following two properties: (1) the system is composed of interacting agents, and (2) the system exhibits emergent properties, that is, properties arising from the interactions of the agents that cannot be deduced simply by agg- gating the properties of the system's components. When the interaction of the agents is contingent on past experience, and especially when the agents continually adapt to that experience, mathematical analysis is typically very limited in its ability to derive the outcome.

This book constitutes the thoroughly refereed joint post-proceedings of five international workshops organized by the Japanese Society of Artificial Intelligence, JSAI in 2001.The 75 revised papers presented were carefully reviewed and selected for inclusion in the volume. In accordance with the five workshops documented, the book offers topical sections on social intelligence design, agent-based approaches in economic and complex social systems, rough set theory and granular computing, chance discovery, and challenges in knowledge discovery and data mining.