Editing Software agent (section)

==Concepts==
The basic attributes of an autonomous software agent are that agents:
* are not strictly invoked for a task, but activate themselves,
* may reside in wait status on a host, perceiving context,
* may get to run status on a host upon starting conditions,
* do not require interaction of user,
* may invoke other tasks including communication.

[[File:Nwana Category of Software Agents.gif|thumb|300px|right|Nwana's Category of Software Agent]]
The concept of an agent provides a convenient and powerful way to describe a complex software entity that is capable of acting with a certain degree of [[autonomy]] in order to accomplish tasks on behalf of its host. But unlike objects, which are defined in terms of ''methods'' and ''attributes'', an agent is defined in terms of its behavior.<ref>{{cite journal |last1=Wooldridge |first1=M. |last2=Jennings |first2=N. R. |year=1995 |title=Intelligent agents: theory and practice |journal=Knowledge Engineering Review |publisher= |volume=10 |issue=2 |pages=115–152}}</ref>

Various authors have proposed different definitions of agents, these commonly include concepts such as:
* ''persistence: c''ode is not executed on demand but runs continuously and decides for itself when it should perform some activity;
* ''autonomy:'' agents have capabilities of task selection, prioritization, goal-directed behavior, decision-making without human intervention;
* ''social ability:'' agents are able to engage other components through some sort of communication and coordination, they may collaborate on a task;
* ''reactivity:'' agents perceive the context in which they operate and react to it appropriately.

===Distinguishing agents from programs===
All agents are programs, but not all programs are agents. Contrasting the term with related concepts may help clarify its meaning. Franklin & Graesser (1997)<ref>{{cite book
 | chapter         = Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents
 | last1         = Franklin
 | first1        = S.
 | title = Intelligent Agents III Agent Theories, Architectures, and Languages
 | volume = 1193
 | pages = 21–35
 | last2         = Graesser
 | first2        = A.
 | year          = 1996
 | publisher     = University of Memphis, Institute for Intelligent Systems
 | doi = 10.1007/BFb0013570
 | series = Lecture Notes in Computer Science
 | isbn = 978-3-540-62507-0
 }}</ref> discuss four key notions that distinguish agents from arbitrary programs: reaction to the environment, autonomy, goal-orientation and [[Persistence (computer science)|persistence]].

===Intuitive distinguishing agents from objects===
* Agents are more autonomous than [[object (computer science)|objects]].
* Agents have flexible behavior: [[Reactive programming|reactive]], [[proactive]], social.
* Agents have at least one [[thread (computer science)|thread]] of control but may have more.<ref name=Woldridge2002>{{cite book |last=Wooldridge |first=Michael J. |date=2002 |title=An Introduction to Multiagent Systems |url=https://www.amazon.com/gp/product/047149691X/#reader_047149691X |publisher=John Wiley & Sons |location=New York |page=27 |isbn=978-0-471-49691-5}}</ref>

===Distinguishing agents from expert systems===
* [[Expert system]]s are not coupled to their environment.
* Expert systems are not designed for reactive, proactive behavior.
* Expert systems do not consider social ability.<ref name=Woldridge2002/>

===Distinguishing intelligent software agents from intelligent agents in AI===
* [[Intelligent agent]]s (also known as [[rational agent]]s) are not just computer programs: they may also be machines, human beings, communities of human beings (such as [[business entity|firm]]s) or anything that is capable of goal-directed behavior.
: {{Harv|Russell|Norvig|2003}}