Topic · 12 concepts

Agents

When LLMs become decision-makers in a loop.

Agentic systems use an LLM to decide which actions to take, observe their results, and continue. The concepts below cover the building blocks — tool use, function calling, planning, trajectory pruning — and the operational patterns that make agent loops reliable enough to ship. Specialized small models increasingly handle the narrow tasks inside agents (tool selection, argument extraction, sub-task decomposition) while the LLM does the open-ended reasoning.

Other topics
ZeroEntropy
The best AI teams build with ZeroEntropy models
Follow us on
GitHubTwitterSlackLinkedInDiscord