Meta 发布并部署了 A-MLE 智能体框架，用于自动化广告排序模型的机器学习实验流程，包括提出想法、运行实验、恢复失败任务、比较结果以及把经验迁移到其他模型。在 Meta 的基础能力测试中，通用 LLM 得分为 8%，配备领域知识的智能体达到 68%。在一个实验性排序模型上，更广的探索使离线回归误差相对基线降低 2.56%，训练 QPS 基本持平，为 +0.42%。
Meta published A-MLE, a new AI agent framework they actually built and deployed to automate ML experimentation across their ads-ranking models.
All because, production ML is often limited by how fast engineers can test ideas.
A-MLE, Meta's automates the repetitive loop behind improving ads-ranking models: proposing ideas, running experiments, recovering failed jobs, comparing results, and carrying useful lessons to other models.
A generic LLM scored 8% on Meta’s basic capability test, while the domain-equipped agent reached 68%.
On 1 experimental ranking model, broader exploration cut offline regression error by 2.56% relative to baseline while training QPS stayed essentially unchanged at +0.42%.
来源：@rohanpaul_ai · x.com