Panel Summary: Agent Development Tools Joanna Bryson 1 , Keith Decker 2 , Scott A. DeLoach 3 , Michael Huhns 4 , and Michael Wooldridge 5 1 Department of Computer Science Massachusetts Institute of Technology, Cambridge, MA 00000 joanna@ai.mit.edu 2 Department of Computer and Information Sciences University of Delaware, Newark, DE 19716-2586 decker@cis.udel.edu 3 Department of Electrical and Computer Engineering, Air Force Institute of Technology 2950 P Street, Wright-Patterson AFB, OH 45433-7765 sdeloach@computer.org 4 Electrical and Computer Engineering Department University of South Carolina, Columbia, SC 29208 huhns@ece.sc.edu 5 Department of Computer Science University of Liverpool Liverpool L69 7ZF, UK m.j.wooldridge@csc.liv.ac.uk 1 Introduction This panel (and a corresponding paper track) sought to examine the state of the art (or lack thereof) in tools for developing agents and agent systems. In this context, “tools” include complete agent programming environments, testbeds, environment simulators, component libraries, and specification tools. In the past few years, the field has gone from a situation where almost all implementations were created from scratch in general purpose programming languages, through the appearance of the first generally avail- able public libraries (for example, the venerable Lockeed “KAPI” (KQML API) of the mid-90’s [10]), to full-blown GUI-supported development environments. For ex- ample, http://www.agentbuilder.com/AgentTools/ lists 25 commercial and 40 academic projects, many of which are publicly available. The sheer number of projects brings up many questions beyond those related to the tools themselves, and we put the following to our panel members: – What are useful metrics or simply feature classes for comparing and contrasting agent development tools or methodologies (especially features that are unique to agent systems)? – How does a tool suggest/support/enforce a particular design methodology, theory of agency, architecture, or agent language? – Why, as more and more development tools and methodologies become available, do most systems still seem to be developed without any specialized tools? – What are the differences in development tools oriented toward the research commu- nity versus the agent application community, and are we already seeing a significant lag between theory and practice? C. Castelfranchi, Y. Lesp´ erance (Eds.): Intelligent Agents VII, LNAI 1986, pp. 331–338, 2001. c  Springer-Verlag Berlin Heidelberg 2001