In computer science, an Intelligent Agent (IA) refers to a software agent that exhibits some form of artificial intelligence. While the working of software agents used for operator assistance or data mining (sometimes refered to as bots), are often based on fixed pre-programmed rules, intelligent here implies the ability to adapt and learn.

In some literature IAs are also refered to as autonomous intelligent agents , although autonomy is generally assumed for agents. According to Nicola Kasabov [http://www.rsnz.org/members/fellows/personal/34686.php] IA systems should exibit the following characteristics:

*learn and improve through interaction with the environment (embodiment) *adapt online and in real time *learn quickly from large amounts of data *accommodate new problem solving rules incrementally *have memory based exemplar storage and retrieval capacities *have parameters to represent short and long term memory, age, forgetting, etc. *be able to analyse itself in terms of behaviour, error and success

= Also see=

*Agent environment - discussion of environment types *Fuzzy agents - IA implimented with adaptive fuzzy logic *Cognitive agents - IA considered to be self-aware *Multi-agent system - multiple interacive agents *Reinforcement learning *Cybernetics *Semantic web - technolgies to use data meaning to automate agents *Federated search - the ability for agents to search heterogeneous data sources using a single vocabulary

= References =