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:
- 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.
- 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.
- 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.