Large language model
A model trained on very large amounts of text to predict likely text, used by most agents to interpret instructions and choose steps.
A large language model is a machine-learning model trained on very large amounts of text to predict likely continuations of text, which lets it summarise, classify, draft and answer questions. Most AI agents use one as the component that interprets instructions and proposes the next step. Its outputs are probabilistic, so they can be fluent and wrong at the same time, which is why agent designs surround the model with deterministic checks.
Agent Minute explains this term on 2 November 2026.
Related terms
AI agentSoftware built on an AI model that pursues a set goal by planning steps and acting through tools or APIs, not only by answering.ConfabulationConfidently stated but false or erroneous output from a generative AI system, often called hallucination.System promptThe standing instructions an operator gives a model before any user input, describing its role, rules and tools.Retrieval-augmented generationRetrieving relevant documents or records first and giving them to the model, so its answer rests on current material.