Facebook Engineering


Meta's Ranking Engineer Agent (REA) is an autonomous AI agent that manages the end-to-end ML lifecycle for ads ranking models. It uses a hibernate-and-wake mechanism to handle multi-day asynchronous workflows, a dual-source hypothesis engine combining historical experiment data with an ML research agent, and a three-phase planning framework (Validation, Combination, Exploitation). In its first production rollout across six models, REA doubled average model accuracy over baseline and enabled three engineers to deliver improvements for eight models — work that previously required two engineers per model, representing a 5x productivity gain.

Ranking Engineer Agent (REA): The Autonomous AI Agent Accelerating Meta’s Ads Ranking Innovation

The Bottleneck in Traditional ML Experimentation

Introducing REA: A New Kind of Autonomous Agent

How REA Manages Multi-Day ML Workflows Autonomously

Impact: Model Accuracy and Engineering Productivity

The Future of Human-AI Collaboration in ML Engineering