跳到正文
每分钟自动更新
  1. AWS Machine Learning Blog

    Evaluating multi-agent systems for explainability and helpfulness with Amazon Bedrock AgentCore

    中文摘要

    多智能体系统需要比流畅响应更深入的保障:它们必须选择正确的工具,遵守约束条件,并解释其决策。了解如何构建基于Strands的多智能体供应链决策系统,并使用Amazon Bedrock AgentCore评估,通过内置、自定义和可解释性评估器对其进行评估。

    英文原文

    Multi-agent systems need deeper guarantees than fluent responses: they must select the right tools, respect constraints, and explain their decisions. Learn how to build a Strands-based multi-agent supply chain decisioning system and evaluate it with Amazon Bedrock AgentCore Evaluations using built-in, custom, and explainability evaluators.

  1. AWS Machine Learning Blog

    Uplifting conversion across the acquisition funnel with personalization using contextual bandits on AWS

    中文摘要

    生成式AI使得大规模生产个性化内容变得成本低廉,但你该向每个客户展示哪种变体呢?亚马逊支付(Amazon Payments)在Amazon SageMaker AI上使用了多目标上下文老虎机算法来个性化获取流程,使某一受众的单位数转化率有所提升,并且了解到是内容而非模型成为了限制因素。

    英文原文

    Generative AI makes it cheap to produce personalized content at scale, but which variation do you show each customer? Amazon Payments used a multi-objective contextual bandit on Amazon SageMaker AI to personalize an acquisition funnel, achieving a high single-digit conversion lift for one audience, and learning why content, not the model, was the constraint.

  1. AWS Machine Learning Blog

    How uniopen customized Amazon Nova to their retail moderation policies for production deployment

    中文摘要

    查看台湾统一企业集团的零售平台 uniopen 如何使用 Amazon SageMaker AI 中的监督微调和提示优化,将 Amazon Nova 2 Lite 适配其内容审核政策。业务相关的评估和发布门禁机制确保了质量。

    英文原文

    See how uniopen, a retail platform from Taiwan's Uni-President Enterprises Group, adapted Amazon Nova 2 Lite to its content-moderation policies using supervised fine-tuning in Amazon SageMaker AI and prompt optimization. Business-relevant evaluation and release gates kept quality in check.

已经到底了