研究人员开发了HASTE，一个旨在提高机器学习工程代理效率的分层多代理系统。通过将知识组织成全局、领域和特定竞赛的层级，HASTE允许代理在不同竞赛之间迁移学习到的技能，减少了从头开始解决问题的需求。这种方法显著提高了性能，在对照测试中达到了100%的奖牌率，而平坦加载的成功率为62.5%，并在热启动场景中使用了更少的优化迭代。 AI
影响 这项研究表明，改进AI代理的知识组织可以显著减少计算和优化需求，从而可能加速机器学习工程工作流程。
排序理由 该集群包含一篇详细介绍新系统和基准测试结果的学术论文。
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.30911v1 Announce Type: new Abstract: ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchical multi-agent system that organizes cross-competition knowledge into three scope tiers (glo…
ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchical multi-agent system that organizes cross-competition knowledge into three scope tiers (global, domain, and competition-specific), each cou…
ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchical multi-agent system that organizes cross-competition knowledge into three scope tiers (global, domain, and competition-specific), each cou…