Meta's Ranking Engineer Agent (REA) doubles model accuracy and delivers 5x engineering output in autonomous ML experimentation
Traditional ML experimentation at Meta was time-consuming and manual: engineers had to craft hypotheses, design experiments, launch training runs, debug failures across complex codebases, and iterate — each full cycle spanning days to weeks. As models matured, finding meaningful improvements became increasingly challenging, making the manual sequential process a bottleneck to innovation.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Engineer initiates experiment plan
An engineer collaborates with the hypothesis generator to create a detailed experiment plan through the REA Planner.
In its first production rollout across six models, REA doubled average model accuracy over baseline and enabled three engineers to deliver proposals for eight models — work that historically required two engineers per model, representing a 5x increase in engineering output. Early adopters increased their model-improvement proposals from one to five in the same time frame.
What failed first
Existing AI tools used in ML workflows functioned as reactive, session-bound assistants that could help with individual steps but could not run an experiment end to end, requiring engineers to re-establish context and manually drive progress across long-running jobs.