AI 每日快讯
AI 产品、模型、开源工具和官方动态的时间流。保留历史记录，按分类、日期和标签继续筛选。
原文摘要：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 Amaz 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：NarrateAI delivers production-ready LLM quality assurance on Amazon Bedrock. This post details five techniques—adaptive pipeline orchestration, cross-account multi-model failover, 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Skills let you encode domain-specific procedures as reusable, portable instructions for agents, but a fluent answer doesn't prove the agent picked the right skill or followed it. L 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Concurrency sweeps help you right-size a generative AI endpoint on Amazon SageMaker AI by systematically benchmarking it at increasing load levels. This post walks through deployin 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn how Tata Elxsi built IRIS, a real-time industrial safety platform on AWS. IRIS filters camera video at the edge, streams metadata through Amazon Kinesis, runs computer vision 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Migrate a multi-model healthcare AI agent from self-managed Amazon ECS with AWS Fargate to Amazon Bedrock AgentCore runtime, preserving triple-model orchestration and vector-enhanc 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Amazon Connect Talent is an AI hiring solution built for talent acquisition leaders managing scaled hiring. It delivers AI-led interviews, data-driven assessments, and consistent e 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Service, Amazon Aurora Po 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn how to build a synthetic data augmentation pipeline on Amazon SageMaker AI and Amazon Rekognition that generates photo-realistic, auto-labeled training images for industrial 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Integrate NVIDIA Resiliency Extension (NVRx) into PyTorch FSDP training on Amazon EKS to overlap checkpoint I/O with training and recover from GPU faults in seconds. This post cove 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-sou 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：AgentCore optimization turns production traces into proposed configuration changes, then validates them before promotion. This technical companion to the launch post explains how t 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Comparing models on dollars per million tokens misses what production workloads actually pay for: outcomes. This post shares an open-source benchmarking harness that measures cost 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Multi-agent systems fail in ways traditional monitoring misses. This post presents a dual-layer approach to monitoring production agents: Amazon Bedrock AgentCore 评测 for c 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Amazon SageMaker Inference now offers prefix-aware routing, a routing strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. I 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Multi-turn agents fail in ways single-turn 评测 misses: one early mistake corrupts every later turn. This post introduces the Agent 评测 Metric (AEM), a decomposable, t 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Pathway's Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought tokens. See how Pathway d 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Managed MLflow on Amazon SageMaker AI now syncs richer model metadata (training metrics, 评测 results, inference specs, and lineage) into the SageMaker AI Model Registry, wit 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：评测 two 30B Mixture-of-Experts models, Qwen3-Coder-30B and NVIDIA Nemotron-3-Nano-30B, across G5, G6, G6e, and G7 GPU instances on Amazon SageMaker AI. Compare throughput, la 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Wire Amazon Bedrock AgentCore 评测 into a GitHub Actions pipeline: deploy an AI agent and an OAuth-protected MCP server to AgentCore runtime, invoke the agent with test prom 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Building a Physical AI system takes a continuous pipeline, not a single training job. This post shows how to run that model factory (synthetic data generation, post-training, and c 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn best practices for building production-grade, agent-based business process automations with Amazon Quick Automate: choosing the right process, designing focused agents, combi 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn how to build a generative AI-based support operations platform on AWS that converts training videos into structured SOPs, applies Retrieval-Augmented Generation to guide tick 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：We're excited to share that AWS has been recognized as a Leader in The Forrester Wave: AI Infrastructure Solutions, Q4 2025. In this 评测 of 13 providers, AWS received the hi 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：This post builds an enterprise agentic retrieval solution on the Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore. An agent reasons, routes across multiple knowle 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn how to build a multi-tenant agentic document chat application on Amazon Bedrock Managed Knowledge Base, where users upload documents and immediately ask grounded questions. T 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Amazon Bedrock AgentCore 评测 decouples agent 评测 from the framework you build on. As long as your agent emits OpenTelemetry telemetry, the service can score it, whet 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Data preparation determines the ceiling of any supervised fine-tuning project. This first post in a two-part series covers the foundations of SFT data prep: quality checks, convers 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：The advanced side of supervised fine-tuning data prep. This second post in a two-part series covers evaluating data readiness with learning curves, selecting high-value data subset 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn how to build a customizable, smart-caching knowledge management system on AWS that captures and delivers institutional (tribal) knowledge through a voice-first AI avatar. The 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Input tokens are often a meaningful part of the cost of running Retrieval Augmented Generation (RAG) at scale. This post describes a query-aware context compression pattern on Amaz 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Learn how to build a multi-agent M&A due diligence system on Amazon Bedrock AgentCore. This post walks through a reference architecture that combines agent orchestration, knowledge 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Temporal policies in Amazon Bedrock AgentCore let you define stateful rules that evaluate authorization based on an agent's session history. Learn how to enforce 工作流 sequencin 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：The Amazon SageMaker Python SDK v3 now exposes generative AI inference recommendations in Amazon SageMaker AI directly in your notebook. 评测 an endpoint, generate data-driven 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we explain how Amazon Bedrock Guardrails can be configured for code generation 工作流 with coding assistants to overcome these constraints. With these best practic 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Together, Motorway and AWS built an end-to-end 评测 pipeline that reduced incorrect results from 1 in 8 queries to 1 in 50 and cut issue detection time from few hours to few 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：This post focuses on why classic retrieval falls short on multi-part questions, how the AgenticRetrieveStream API works (including request construction and trace parsing), and when 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we explore an idea for generating thinking tokens for datasets that lack reasoning traces in SFT customization. We first examine the reasoning suppression problem, th 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we walk through the three pillars that make this possible: simplified setup, smarter retrieval, and production readiness. We also show you code examples for setting u 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Built partnered with the AWS Generative AI Innovation Center (GenAIIC), AWS Partner AND Digital, and AWS account teams to create a scalable, AI-powered document processing engine t 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：This post shows how Thrad.ai deployed a multi-agent system with Strands Agents and Amazon Bedrock AgentCore that automates the pipeline from prospect discovery through personalized 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we introduce the UI for optimized generative AI inference recommendations in Amazon SageMaker AI Studio, a low-code no-code (LCNC) experience. The API already gives y 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：This post describes how Henry Schein One closed that gap by building Image Verify, an AI-powered quality verification system on Amazon SageMaker AI that evaluates dental X-ray qual 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we explore how Graph-based Retrieval Augmented Generation (GraphRAG) is transforming scientific research by combining graph databases with generative AI. With this ap 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, you learn how to use the new MLflow integration with Amazon SageMaker AI optimized inference recommendation jobs and Amazon SageMaker AI 评测 jobs to automatical 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we share best practices for reliable multi-turn RL training. We cover how to build a training environment you can trust, set up an external 评测, design a rewar 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, you will learn how metadata works across configuration, ingestion, and retrieval, explore enterprise use cases including multi-agent and multi-tenant architectures, a 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we walk through the problem space, our architecture on Amazon Bedrock and Amazon OpenSearch Serverless, the 评测 methodology we built on OpenStreetMap ground tr 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Today, we’re announcing a new API with Amazon Bedrock Guardrails. With this API, you can apply individual safeguards, also referred to as safety checks, at any point in your agenti 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we walk you through calling the detector functions to diagnose real agent failures. You learn how to interpret their structured output: categorized failures with conf 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Agent-EvalKit is an open-source toolkit (Apache 2.0) that makes this 评测 infrastructure available by integrating with AI coding assistants, including Claude Code, Kiro CLI, 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, you build an AI-powered equipment repair assistant using Amazon Bedrock AgentCore that helps farmers and field technicians diagnose equipment problems, identify requi 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, you learn how to use Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) together to improve the tool-calling accuracy of a small language model (SL 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：This post combines learnings from LangChain’s work on evaluating deep agents and Anthropic’s guide to demystifying evals for AI agents into a practical guide. In this post, you wil 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Agent 评测 is most powerful when you combine fast-moving online signals with stable offline baselines. To understand whether your agent is truly improving over time, you need 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post you'll learn how to build a multi-agent campaign review system that demonstrates parallel reasoning, context persistence, and traceable execution paths using an integr 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we show you how OPLOG developed three AI agents using the Strands Agents SDK, deployed them to Amazon Bedrock AgentCore, and integrated Amazon Bedrock with Anthropic’ 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we demonstrate how to build an AI-powered recruitment assistant using Amazon Bedrock that brings efficiencies to candidate 评测, generates personalized intervie 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：If you’re building visual shopping, image or document understanding, or chart analysis, you need a way to verify whether your model’s response is actually grounded in the source im 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, you learn how to prompt Amazon Nova 2 Lite for content moderation using structured and free-form approaches, grounded in the MLCommons AILuminate Assessment Standard. 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, you will implement four Lambda-based custom code evaluators for a financial market-intelligence agent, register each with AgentCore, and run them in on-demand and onl 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we build a multimodal retrieval system for aerospace manufacturing documents using Amazon Nova Multimodal Embeddings on Amazon Bedrock and Amazon S3 Vectors. We evalu 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：In this post, we'll explore how we built a proof-of-concept that converts natural language queries into executable seismic 工作流 while providing a question-answering capability 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。
原文摘要：Today, we’re excited to announce that Amazon SageMaker AI MLflow Apps now support MLflow version 3.10, bringing enhanced capabilities for generative AI development and streamlined 来源：AWS Machine Learning 动态。建议继续查看原文，重点核对它影响的工具入口、成本、风险和真实使用场景。