Ranking Engineer Agent (REA): 加速 Meta 的广告排序创新的自主 AI 代理

Meta’s Ranking Engineer Agent (REA) autonomously executes key steps across the end-to-end machine learning (ML) lifecycle for ads ranking models.
Meta’s Ranking Engineer Agent (REA) 自主执行广告排名模型端到端 machine learning (ML) 生命周期中的关键步骤。
This post covers REA’s ML experimentation capabilities: autonomously generating hypotheses, launching training jobs, debugging failures, and iterating on results. Future posts will cover additional REA capabilities.
这篇文章介绍了 REA 的 ML 实验能力：自主生成假设、启动训练作业、调试失败并迭代结果。后续文章将介绍 REA 的其他能力。
REA reduces the need for manual intervention. It manages asynchronous workflows spanning days to weeks through a hibernate-and-wake mechanism, with human oversight at key strategic decision points.
REA 减少了对手动干预的需求。它通过休眠和唤醒机制管理跨越数天到数周的异步工作流程，并在关键战略决策点进行人类监督。
In its first production rollout, REA delivered:
- 2x Model Accuracy: REA-driven iterations doubled average model accuracy over baseline across six models.
- 5x Engineering Output: With REA-driven iteration, three engineers delivered proposals to launch improvements for eight models — work that historically required two engineers per model.
在首次生产部署中，REA 实现了：
- 2x 模型准确率： REA 驱动的迭代使六个模型的平均模型准确率相对于基线翻倍。
- 5x 工程产出： 通过 REA 驱动的迭代，三名工程师为八个模型提供了启动改进的提案——这项工作历史上需要每模型两名工程师。

Meta’s advertising system delivers personalized experiences to billions of people across Facebook, Instagram, Messenger, and WhatsApp. Powering these interactions are highly sophisticated, complex and massively distributed machine learning (ML) models that continuously evolve to serve both advertisers and people who use the platforms.

Meta 的广告系统为 Facebook、Instagram、Messenger 和 WhatsApp 上的数十亿用户提供个性化体验。驱动这些互动的是高度复杂、庞大且大规模分布的 machine learning (ML) 模型，这些模型不断演进，以服务广告主和使用平台的人们。

Optimizing these ML models has traditionally been time-consuming. Engineers craft hypotheses, design experiments, launch training runs, debug failures across complex codebases, analyze results and iterate. Each full cycle can span days to weeks. As Meta’s models have matured over the years, finding meaningful improvements has become i...