An agent is capable of flexible and autonomous action in a dynamic environment. In the sense that the new agent-based technology paradigm causes a re-evaluation of the very nature of computing, computation and computational system through concepts. It means that agents need to be able to engage in interaction, to negotiate, to make pro-active run-time decision and to allocate and schedule resources across the diverse competing demands places on infrastructure and systems. A truly effective internet agent needs to be able to work for the user when the user isn't directly in control. In such systems the internet agent varies its autonomy based on factors like costs, the resources needed, or other variables such as softgoal or non-functional requirements that the user might wish to control.
However, enabling autonomy is a difficult programming task, particularly because it is very dependent on features of the area in which a program is operating. For human agents the level of autonomy is clearly defined, sometimes by law, sometimes by customs that have grown up over many years. For internet agents it is much less clear. It is even unclear whether the variation among tasks will be high or low for internet agents. For example, it seems unlikely that an agent helping find, order and download physics papers would be much different from one in biology. In the current situation, an internet agent with predetermined pages to visit is quite limited. Thus, a truly useful agent should be able to adapt its behavior based on a combination of user feedback and environmental factors.
For an agent to be capable, it must be able to take action in some sort of world. The difference between an agent and an (internet) advisor, is that the agent not only provides advice, but also provides a service, the ability to do things on the Web without you needing to know the details. Unfortunately, the current state of the art is limited by the need to know much about the specifics of the internet sources the agent will interact with. For example, suppose you want a paper from some particular physics journal, but the journal charges for it. If you want an internet agent to be able to download this paper for you, it would need to know where on the page the price is, where it communicates your credit card number, in what formats the various pieces of information about you need to be put, etc.
Many researches believe that the contents of the websites should be understood by the machine just like we understand how to read the meaning of the websites so then the agent should work in the higher level based on the information that machine understands about the website.Then, I believe that there is no way agent-based technology will work properly if there are no such machines that intelligently be able to reason the knowledge described in the websites.