agent

AI (general)

Anything that takes in information about its surroundings and does something that affects them: a thermostat, a robot, a trading program or a person. Since Stuart Russell and Peter Norvig's textbook (1995), which defines an agent as perceiving its environmentenvironment, n.: Everything an AI agent interacts with but does not control — a game, a simulator, a website, the physical world. It answers each of the agent's actions with a new situation and, in reinforcement learning, a score. through sensors and acting on it through actuators, AI is often described as the design of agents that act rationally, choosing actions expected to best achieve a performance measure given what they perceive and know; see intelligent agentintelligent agent, n.: In AI theory, a decision-maker, such as a robot, a self-driving car, a chess program or a helpful piece of software, that notices what is going on around it and responds in ways that serve its goals.. Agents are characterized by their sensors, actuators and environment, and by how far they rely on built-in knowledge versus learning.

Reinforcement learning

The learner and decision-maker in a reinforcement learningreinforcement learning, n.: A way of teaching a computer program by trial and error: it tries actions, earns points for good results and penalties for bad ones, and gradually learns which choices pay off over time. problem, which repeatedly observes a statestate, n.: A snapshot of the situation an AI agent is in — for a chess program, the arrangement of pieces and whose turn it is — containing what it needs to decide what to do next., chooses an actionaction, n.: A choice an AI agent makes at one moment — move left, place a stone, type a command — which changes its situation and may earn it a reward. according to its policypolicy, n.: An AI agent's strategy: the rule it follows to pick an action in each situation. Training in reinforcement learning means improving this rule until it earns high rewards. and receives a rewardreward, n.: The score an AI system receives after an action, telling it how good the outcome was. Reinforcement learning trains the system to collect as much reward as possible over time. from the environment, aiming to maximize cumulative reward. The agent–environment boundary is drawn at what the agent controls directly, not at a physical body.

Language-model systems

Short for AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done.: a system in which a large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. runs in an agent loopagent loop, n.: The repeating cycle at the heart of an AI agent: the model decides what to do next, software carries it out, the result is shown to the model, and the cycle repeats until the task is finished., choosing and calling toolstool, n.: Any outside capability an AI model is allowed to use — a web search, a calculator, a code runner, a database or an app — described to the model so it can ask for it by name. and acting on their results over many steps to accomplish a goal, inside a harnessharness, n.: The software around an AI model that gives it instructions and tools, carries out its actions and decides when it stops. The model is the engine; the harness is the rest of the car. that executes its actions. This sense, dominant since 2024, overlaps with agentic AIagentic AI, n.: AI built to pursue goals on its own — planning, taking actions and adjusting along the way — instead of only responding to one prompt at a time. 'Agentic' describes how much of this independence a system has.; systems of several cooperating agents are multi-agent systemsmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves., and agents spawned by another agent are subagentssubagent, n.: A helper AI agent that a main agent starts to handle one piece of a job; it works in its own separate workspace and reports back a short summary when it is done..

The agent opened a branch, ran the test suite and fixed two failures before asking for review.

Software engineering

An autonomous software process that acts on behalf of a user or another program, as in the software agents and agent-oriented programming of the 1990s, or a monitoring process installed on a server. In web standards a user agent is the browser or other client acting for the user.

Philosophy and law

A being capable of intentional action, one that has agency; and, in law and economics, a party authorized to act for a principal. Both senses shape debates over whether AI systems have agency, who is responsible for their acts, and how principal–agent relations apply when software buys, books or negotiates for people, as in agentic commerceagentic commerce, n.: Shopping and payments carried out by AI agents for people — finding products, comparing offers and completing purchases — within limits the person has approved..