Strawman Agent Reference Architecture (DARPA ISO coABS Program - Draft 11-30-98) Craig Thompson

1. Strawman Agent Reference Architecture (DARPA ISO coABS Program - Draft 11-30-98) Craig Thompson Object Services and Consulting, Inc. (OBJS) thompson@objs.com, http://www.objs.com

2. Agent Reference Architecture Requirements • Target operational requirements: • Networked society where everything is alive -- every software artifact, information source, and device is connected and running in parallel. Humans and agents connect to the agent grid anytime from anywhere and get the information and capability they need. Enable teams led by humans and staffed by agents. • Intelligent automation -- easier application connectivity where networks of agents self-organized at run-time. Reduce the 60% of time in command and control systems spent manipulating stovepipes; incrementally replace stovepipes. • Connect the $40B worth of DoD equipment that currently only interoperates with one or two other components, permitting better knowledge sharing. Another example is a process improvement in factory 1 is broadcast immediately to factories 2..N. • Agent-enable object and web applications to reconfigure as new data and function is added to the system. Scale to millions of agents so agents are pervasive and information and computation is not restricted to machine or organization boundaries; if one agent goes down, another takes its place; add capability modularly; stable, scaleable, evolvable, reliable, secure, survivable, ...

3. Agents dynamically adapt to and learn about their environment Agents coordinate and negotiate to achieve common goals social personality social personality Adaptive to uncertainty and change Adaptive Cooperative self-organizing delegation Cooperative Autonomous proactive Autonomous Mobile Mobile Interoperate Interoperate Agents move to where they are needed Agents interoperate with humans, other, legacy systems, and information sources Agents are goal directed and act on their own performing tasks on your behalf Characteristics of Agents

4. A A A A A A A Server Server A A A Server Server Data Service Data Service A A A A A A A A A A A A Component Library Component Library A A A A A A A A A A System Concept View Agents + the Global Software Grid Relevant Theory • speech acts, conversations/dialogs • ontologies • game theory • economic markets • patterns and protocols • planning & case-based reasoning • learning • KBMS • workflow • dynamic DBMS • simulation • architecture description languages • distributed AI • component technology • Web architectures • frameworks (Jini) • OO middleware services (OMA/ORB) • network management and QoS

5. Architecture Principle: separation of concerns deconstructionist view - what can you take away and still have an agent system Agent Architecture Details • policy*, management • resource dial ALP, HLA, IA GRID federates • AGENT SYSTEM • single vs. multi-agent • heterogeneous* • computing environ. • agent systems • ACLs • content languages • ontologies • policies • services • open world assumption systemic grid features common services • ensembles • # of agents* • teams, peers, contracting, • org. responsibility • roles, capabilities, • mutual beliefs • hierarchy* • conversational policies* • societies • closed vs. open, communities of interest • agent properties & kinds • communication capability • computation capability • by role in system • information agent • data sources • interface agent • NL • fisheye view • task agent • web agent • middleware agent • mobile agent, itinerary • social, personality, motivation, forgetting • intelligent agent distribution messaging svcs* agent life cycle* - start, stop, checkpoint, name service** event monitoring leasing, compensation catalog services*, registry/repository* register*, offer/accept/decline publish*, subscribe* trading*, matchmaking, advertising*, negotiating*, brokering*, yellow pages* security** authenticate* encrypt access control lists* firewall* CIA model agent suspects transactions persistence* query, profile (of metadata)* data fusion replication* groups multicast (scarce) resource mgmt*, allocate*, deallocate*, monitor*, local, global optimization, load balancing*, negotiation for resources* scheduling time, geo-location rules, constraints planning* property list versioning, config autonomous decentralized* • control*, coordination*, • multi-agent synchronization • cooperation, competition I*3 BADD AICE OMG JTF Jini scalability* adaptation, evolution* via market model, ... licensing & cost mobility** • ONTOLOGY** • ontolingua, OKBC • metadata representations • interests, locations, availability, capability, price/cost • XML and web object models secure*, trust IA speech acts*: ACL* - KQML, FIPA ACL, OAA ICL survivability • planning* • reactive* • goal interactions* • discrete vs continuous* • constraints • iterative, revision • workflow • infrastructure • primitives • reflection • serialization • threads • interceptors • proxies • filters • multicast • wrappers • legacy sys • data sources evolvability EDCS • missing • views • MOP reliabile* • QoS* • accuracy • priorities Quorum • learning • by example • ... More common services instrumenting, logging caching queuing routing, rerouting pedigree, drill down translation* ... time-constrained* • content languages • KIF, FOL, IDL, RDF * = Architecture WG in Pittsburg * = Control WG in Pittsburg * = Interoperability WG in Pittsburg red = Sun Jini green = other DARPA programs DDB

6. Architecture Issues • What are agents? - code and data packets that are autonomous, adaptive, cooperative, mobile, interoperable … We want all these properties in future agent-based systems. We need experience building systems with these properties. • Pervasiveness - How do we insure that the architecture stays lite-weight for wide-spread adoption. • Embracing heterogeneity - We must piggyback agent systems on already pervasive infrastructure like ORBs, the Web, email, and DBMS systems. We must identify the specific kinds of heterogeneity we want agent system architectures to support. • Separation of concerns • agent-agent separation - can agents access each other’s state directly • agent-service separation - do agents implement the long list of services that the grid provides or is that done via underlying component-based middleware? • grid-agent separation - agents are autonomous but they cooperate and compete for resources within the software grid. The grid provides some global systemic properties and some basic shared services. Is there an explicit grid or is it implicit in the way agents interact with each other? Are some “services” (like planning) optionally distributed into agents or are they available from the grid’s planing service? Can new services be autoloaded into a grid that does not have them? • Semantic interoperability, ontology - do ontologies scale? How do they extend class libraries? • Licensing - Agents, data sources, and component software need an economic model so broad communities can get value from them. A model of licensing might be critical to success in the large. • Agent communication language (ACL) - Is the ACL compositional and extensible so one can define new speech acts from existing ones? How many speech acts is enough? 20 or 5000? • Control points - where are the control points where different control algorithms might be substituted into the architecture • Grid federation issues - How are software grids federated - flat versus hierarchical models? If different grids contain different policy choices or different services, how does that affect agents communicating across grid boundaries? Can we add new services and -ilities to a grid once it is deployed? how transparent is addition or subtraction of services and ilities • Coordination - Insure Agent Reference Architecture augments DARPA ISO ATAIS architecture. Provide template for next generation unified OMG, FIPA, and W3C agent standards. Insure that reference implementations (toolkits) exist and are widely available.