Software-based Agent

From GM-RKB
(Redirected from Software agent)
Jump to navigation Jump to search

A Software-based Agent is a software system that performs automated tasks on behalf of a user.



References

2024

  • (Wikipedia, 2024) ⇒ https://en.wikipedia.org/wiki/software_agent Retrieved:2024-6-2.
    • In computer science, a software agent is a computer program that acts for a user or another program in a relationship of agency.

      The term agent is derived from the Latin agere (to do): an agreement to act on one's behalf. Such "action on behalf of" implies the authority to decide which, if any, action is appropriate. Some agents are colloquially known as bots, from robot. They may be embodied, as when execution is paired with a robot body, or as software such as a chatbot executing on a computer, such as a mobile device, e.g. Siri. Software agents may be autonomous or work together with other agents or people. Software agents interacting with people (e.g. chatbots, human-robot interaction environments) may possess human-like qualities such as natural language understanding and speech, personality or embody humanoid form (see Asimo).

      Related and derived concepts include intelligent agents (in particular exhibiting some aspects of artificial intelligence, such as reasoning), autonomous agents (capable of modifying the methods of achieving their objectives), distributed agents (being executed on physically distinct computers), multi-agent systems (distributed agents that work together to achieve an objective that could not be accomplished by a single agent acting alone), and mobile agents (agents that can relocate their execution onto different processors).

2024

  • Perplexity
    • It performs automated tasks on behalf of a user or another program with a certain degree of autonomy.
    • It can execute predefined tasks or functions based on specific conditions or events, often without direct human intervention.
    • It ranges from simple scripts that automate repetitive tasks to complex systems employing advanced AI and machine learning algorithms.
    • It exhibits autonomy, making decisions and performing tasks independently without continuous human guidance.
    • It can perceive its environment and respond to changes appropriately, demonstrating reactivity.
    • It can communicate and collaborate with other agents or systems, displaying social ability.
    • It enhances efficiency, reduces manual workloads, and improves task accuracy and speed through automation and data-driven decision-making.

2013

  • http://en.wikipedia.org/wiki/Software_agent
    • QUOTE: In computer science, a systems agent is a computer program that acts for a user or other program in a relationship of agency, which derives from the Latin agere (to do): an agreement to act on one's behalf. Such "action on behalf of" implies the authority to decide which, if any, action is appropriate.[1][2]

      Related and derived concepts include intelligent agents (in particular exhibiting some aspect of artificial intelligence, such as learning and reasoning), autonomous agents (capable of modifying the way in which they achieve their objectives), distributed agents (being executed on physically distinct computers), multi-agent systems (distributed agents that do not have the capabilities to achieve an objective alone and thus must communicate), and mobile agents (agents that can relocate their execution onto different processors).

  1. Nwana, H. S. (1996). Software Agents: An Overview. 11. Cambridge University Press, Knowledge Engineering Review. pp. 205–244.  1996. Software Agents: An Overview. Knowledge Engineering Review, Vol. 11, No. 3, 205-244, Cambridge University Press
  2. Schermer,, B. W. (2007) (paperback). Software agents, surveillance, and the right to privacy: A legislative framework for agent-enabled surveillance. 11. Leiden University Press. pp. 140, 205–244. ISBN 978-0-596-00712-6. Template:Hdl. http://it-ebooks.info/book/252/. Retrieved 2012-10-30. 

2011

1996

1996

  • H. S. Nwana. (1996). “Software Agents: An Overview.” In: Knowledge Engineering Review, 11(3).