This talk presents our experience at IBM in building commercial agents, including philosophy, market opportunities, tools, applications, lessons, and future research directions. IBM has released reusable tools for building agents, including Agent Building Environment based on our group's research. IBM has also built practical intelligent agents applications in e-commerce shopping, customer service, mail, news, and Web information, based in part on our group's research. Agent Building Environment ``situates'' reasoning by augmenting it with clean an d dynamic procedural attachments for perception and action. It is especially useful to enhance ``information-flow'' applications with agents that not only find and filter information items, but also categorize, save, and selectively disseminate them. Some of our latest research responding to practical building lessons includes: conflict handling; learning from observation of users; and learning from inter-agent knowledge-level communication.
By: Benjamin N. Grosof
Published in: RC20835 in 1997
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
;Questions about this service can be mailed to reports@us.ibm.com .