Yenta is still under active development, but this particular page is not. If you're interested in current research papers about Yenta, or obtaining a copy of Yenta, please start here instead. This page is one of many that were written in late 1994 and early 1995, and are being preserved here for historical purposes. If you're viewing this page, you probably found it via an old link or are interested in the history of how Yenta came to be. These pages have not been actively maintained since 1995, so you'll find all sorts of older descriptions which may not match the current system, citations to old papers and old results, and so forth. |
Some applications of agents involve one agent that serves many people "simultaneously". This is certainly the case in agents such as Julia and Ringo. However, there are unfortunate scaling issues in such applications.
Many future extensions of agent techology concern agents working together. This serves two aims:
Such collaborative agents often have their own problems, though. Consider, for example, the collaborative email-filtering agent recently completed in the MIT Media Lab Agents Group. This agent shares database information about what its users find interesting (or not) about their email, so that new agents can learn from the more-established agents of users in the same small group. Unfortunately, however, it does not address:
Yenta attempts to address both these issues.
A note on navigation: The pages describing Yenta are currently a rather bushy hypertext, in the style of Minsky's Society of Mind. A very simple (and temporary!) linearization by topic of them exists, which you might want to refer to if you want to see absolutely every page and don't want to spend a long time wandering around. Eventually, much better navigational aids will be a part of these pages (and the simple linearization above will vanish), but they aren't there yet, so bear with us for now.
Lenny Foner Last modified: Wed Apr 19 01:08:08 1995