Pattern

Evaluator–Optimizer

One LLM generates a candidate; a second LLM evaluates it and produces feedback; the generator revises. Loop until the evaluator accepts or a budget is exhausted.

Classification — Looping

Full entry

The complete treatment — problem, how it works, when to use it, sources, and examples — lives in the volume below.

Vol. 01 Patterns of AI Agent Workflows Workflow & Primitives

Browse the full pattern index or the catalog.