Varying the user interaction within multi-agent systems

Agents within an open multi-agent system are located through their advertisements with middle agents. Such advertisements describe the agent's capability, ontology, query or task specification, and details about the data returned once the task has been completed. Agents may have similar capabilities, but exhibit different models of user interaction. A case study of a multi-agent system is described which contains a variety of different agents, some of which have functionally similar capabilities but involve different types of user interaction. We demonstrate how the choice of user interaction can have a significant effect on the performance of the whole agent community. This leads to the proposal that an agent's interactive style should also be included within its capability advertisement.

[1]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[2]  Timothy W. Finin,et al.  KQML as an agent communication language , 1994, CIKM '94.

[3]  Pat Langley,et al.  An adaptive interactive agent for route advice , 1999, AGENTS '99.

[4]  Katia P. Sycara,et al.  Distributed Intelligent Agents , 1996, IEEE Expert.

[5]  Onn Shehory,et al.  A Planning Component for RETSINA Agents , 1999, ATAL.

[6]  Michael Grüninger,et al.  Introduction , 2002, CACM.

[7]  Christine Collet,et al.  Resource integration using a large knowledge base in Carnot , 1991, Computer.

[8]  Karen Zita Haigh,et al.  Exploiting domain geometry in analogical route planning , 1997, J. Exp. Theor. Artif. Intell..

[9]  Terry R. Payne,et al.  Experience with Rule Induction and k-Nearest Neighbor Methods for Interface Agents that Learn , 1997, IEEE Trans. Knowl. Data Eng..

[10]  Wayne Zachary,et al.  Interface Agents in Complex Systems , 1996 .

[11]  Michael R. Genesereth,et al.  Software agents , 1994, CACM.

[12]  Michael Lewis,et al.  Designing for Human-Agent Interaction , 1998, AI Mag..

[13]  Michael P. Wellman.  A Market-Oriented Programming Environment and its Application to Distributed Multicommodity Flow Problems , 1993, J. Artif. Intell. Res..

[14]  Jeffrey M. Bradshaw,et al.  An introduction to software agents , 1997 .

[15]  Matthias Klusch,et al.  Dynamic service matchmaking among agents in open information environments , 1999, SGMD.

[16]  Nadine B. Sarter,et al.  “From Tool to Agent”: The Evolution of (Cockpit) Automation and Its Impact on Human-Machine Coordination , 1995 .

[17]  Katia Sycara,et al.  Intelligent agents in portfolio management , 1998 .

[18]  Terry R. Payne,et al.  Agent-based team aiding in a time critical task , 2000, Proceedings of the 33rd Annual Hawaii International Conference on System Sciences.

[19]  Helen Nissenbaum,et al.  Software agents and user autonomy , 1997, AGENTS '97.

[20]  Katia P. Sycara,et al.  Designing behaviors for information agents , 1997, AGENTS '97.

[21]  Katia P. Sycara,et al.  Middle-Agents for the Internet , 1997, IJCAI.

[22]  Ian H. Witten,et al.  Teaching Agents to Learn: From User Study to Implementation , 1997, Computer.

[23]  Pattie Maes,et al.  Agents that reduce work and information overload , 1994, CACM.