Multi-Agent Systems





Semantic Web                Technologies

     MultiAgent Systems

     Electronic Commerce

     MAS Management

     Information Gathering
Multi-Agent Learning
MAS Interoperability


Project Grants
Site Map


In artificial intelligence research, agent-based systems technology has been hailed as a new paradigm for conceptualizing, designing, and implementing software systems. Agents are sophisticated computer programs that act autonomously on behalf of their users, across open and distributed environments, to solve a growing number of complex problems. Increasingly, however, applications require multiple agents that can work together. A multi-agent system (MAS) is a loosely coupled network of software agents that interact to solve problems that are beyond the individual capacities or knowledge of each problem solver.

Advantages of a Multi-Agent Approach
An MAS has the following advantages over a single agent or centralized approach:

  • An MAS distributes computational resources and capabilities across a network of interconnected agents. Whereas a centralized system may be plagued by resource limitations, performance bottlenecks, or critical failures, an MAS is decentralized and thus does not suffer from the "single point of failure" problem associated with centralized systems.
  • An MAS allows for the interconnection and interoperation of multiple existing legacy systems. By building an agent wrapper around such systems, they can be inporporated into an agent society.
  • An MAS models problems in terms of autonomous interacting component-agents, which is proving to be a more natural way of representing task allocation, team planning, user preferences, open environments, and so on.
  • An MAS efficiently retrieves, filters, and globally coordinates information from sources that are spatially distributed.
  • An MAS provides solutions in situations where expertise is spatially and temporally distributed.
  • An MAS enhances overall system performance, specifically along the dimensions of computational efficiency, reliability, extensibility, robustness, maintainability, responsiveness, flexibility, and reuse.

Applications of Multi-Agent Research
MAS applications cover a variety of domains, including

We are currently interested in interagent communication and coordination, and are building reusable multi-agent applications that facilitate interaction among different kinds of agent systems.



Copyright 2006 - 2012 © Advanced Agent-Robotics Technology Lab - The Robotics Institute - Carnegie Mellon University

Internal Site (Restricted Access).