RETSINA - Reusable Environment for Task Structured Intelligent Network Agents
The RETSINA framework is being used to develop distributed collections
of intelligent software agents that cooperate asynchronously to
perform goal-directed information retrieval and information
integration in support of performing a variety of decision making
tasks. A collection of RETSINA agents form an open society of reusable
agents that self organize and cooperate in response to task
requirements. In particular, we focus on three crucial
characteristics of the overall framework that differentiate our work
from others:
- we use a multi-agent system where the agents operate
asynchronously and collaborate with each other and their user(s)
- the agents actively seek out information
- information gathering is seamlessly integrated with problem
solving and decision support
This page will discuss motivation, the overall system organization,
and the architectural framework for individual agents. We will draw
examples from our work on Intelligent Agents in the domains of
Organizational Decision Making (the PLEIADES system), and Financial
Portfolio Management (the WARREN system).
Motivations
Agent Organization
Agent Architecture
Agent Architecture: Functional View
Agent Architecture: Detailed Control Flow View
To CMU Intelligent Software Agents Homepage
Pleiades
Last modified: Mon Jun 23 16:14:56 EDT