PulseAugur
中
实时 08:58:21
English(EN) MLE Agents: Autonomous ML Engineering in Large-scale Recommendation Systems

自主机器学习代理推动大规模推荐系统中的实际工程

研究人员开发了自主机器学习工程师(MLE)代理,能够在大型推荐系统中提出、实施、训练和评估模型变更。这些代理在行业规模的搜索排序器中运行,人类工程师负责目标设计和最终模型审查。该系统通过并行训练、校准目标和仔细的上下文工程,解决了反馈周期长、离线指标与在线影响脱节以及性能饱和等挑战。在一个活动中,代理运行了1097次实验,接受率为29.6%,最佳模型在A/B测试中将搜索量提高了0.23%。 AI

影响 展示了自主代理在生产环境中执行复杂机器学习工程任务的潜力,可能加速模型开发和创新。

排序理由 该集群基于一篇arXiv论文,详细介绍了用于自主机器学习工程的新研究方法和系统。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

自主机器学习代理推动大规模推荐系统中的实际工程

本文如何被排名

Signal score
19 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群基于一篇arXiv论文,详细介绍了用于自主机器学习工程的新研究方法和系统。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Matthew Li, Albert Liang, Dilip Raj ·

    MLE Agents:大规模推荐系统中的自主机器学习工程

    arXiv:2611.23910v1 Announce Type: new Abstract: The typical workflow for improving large-scale ranking and recommendation models is slow and tedious: an engineer forms a hypothesis, implements it as a code change, trains a model, and evaluates it both offline and online, often re…