LIMITATIONS OF AGENTS


 

Intelligent agent technology should not be oversold even though it has an important role to play in the development of leading-edge computer applications. Currently, most applications that use agents could be built using non-agent techniques. Also, it should be noted that the very nature of the agent paradigm leads to a number of problems, common to all agent-based applications. They are:
  1. No overall system controller. An agent-based solution may not be appropriate for domains in which global constraints have to be maintained, in domains where a real-time response must be guaranteed, or in domains in which deadlocks or livelocks must be avoided.
  2. No global perspective. By definition, an agent’s actions are determined by that agent’s local state. However, since in almost any realistic agent system, complete global knowledge is not a possibility, this may mean that agents make globally sub-optimal decisions. The issue of reconciling decision making based on local knowledge with the desire to achieve globally optimal performance is a basic issue in multi-agent systems research.
  3. Trust and delegation. For individuals to be comfortable with the idea of delegating tasks to agents, they must first trust them. Both individuals and organizations will thus need to become more accustomed and confident with the notion of autonomous software components, if they are to become widely used. Users have to gain confidence in the agents that work on their behalf , and this process can take time. During this period, the agent must strike a balance between continually seeking guidance ( and needlessly distracting the user ) and never seeking guidance (and exceeding its authority). Put crudely, an agent must know its limitations.

HOME | INTRODUCTION | WHAT IS AN AGENT| EXAMPLES |

|WHY DO WE NEED AGENTS | AGENTS AND SEARCH ENGINES| LIMITATIONS OF AGENTS|

|APPLICATIONS OF INTELLIGENT AGENTS | FUTURE OF AGENTS | REFERENCES|