Agent loop

Also called: agentic loop, agent loops, tool loop, ReAct loop

The repeating cycle that makes an AI agent work: the model decides on a step, calls a tool, reads the result and decides the next step, until the task is done or it stops.

For example: Asked to fix a failing test, a coding agent reads the error, edits a file, reruns the test, sees a new error and loops again until it passes.