Retsina Infrastructure

We are developing a reusable, distributed, multi-agent infrastructure called RETSINA (Reusable Task Structure-based Intelligent Network Agents) to coordinate intelligent agents in gathering, filtering, and integrating information for the Internet and for decision support. RETSINA has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and by carrying out these plans through querying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneous collection of information sources.

For more information, visit the RETSINA Project Page.


Raymond Chung-Man Tam
Constantine Domashnev
Joseph Giampapa
Lu Jianguo
JianBing Li
Dirk Kalp
Matthias Klusch
Anandeep Pannu
Massimo Paolucci
Terry Payne
Marios Savvides
Larry Schuler
Onn Shehory
Gita Sukthankar
Katia Sycara
Martin Van Velsen
Seth Widoff

Multidisciplinary University Research Initiative (MURI)
Principal Investigator: Katia Sycara
Sponsored by: Office of Naval Research (ONR)
ONR Contact: Michael Shneier
1998 Carnegie Mellon Robotics Institute

Carnegie Mellon School of Computer Science Carnegie Mellon Robotics Institute DefenseLINK Office of Naval Research MURI Welcome University of Pittsburgh School of Information Sciences