跳到主要內容
AI News HubLIVE

來源分布

  • LangChain Blog43
  • AWS Machine Learning Blog3
  • MarkTechPost2
  • arXiv Robotics1
  • Hacker News AI1

主題分布

  • Agent50
  • 研究31
  • 模型18
  • 創業融資5

日期線

  • 2026-08-2611
  • 2026-08-279
  • 2026-09-245
  • 2026-09-103
  • 2026-09-132
  • 2026-09-182
  • 2026-10-082
  • 2026-10-092

最新動態

待翻譯:How to build great out-of-the-box user experiences with Managed Deep Agents

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Managed Deep Agents includes a new API for managing reactions for your distributed agents, and a system to dynamically assign emoji responses with your instrument of choice. Learn more.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How to build great out-of-the-box user experiences with Managed Deep Agents

待翻譯:How Snyk Turned an Internal Support Agent into a Customer Feature

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Discover how Snyk transformed an internal support agent into Snyk Assist, a customer-facing AI feature powered by LangChain, LangGraph, and LangSmith.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How Snyk Turned an Internal Support Agent into a Customer Feature

待翻譯:Agents that can pay: building Restock with Stripe's Link and Managed Deep Agents

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Build an agent that pays for real purchases. Restock runs in Slack on Managed Deep Agents and pays with Stripe's Link over the Machine Payments Protocol.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Agents that can pay: building Restock with Stripe's Link and Managed Deep Agents

待翻譯:Revamping Skills in Deep Agents

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Deep Agents now lets you bind tools to skills, pin skills at runtime, and reload skills mid-thread, so agents with expansive skill repositories stay context-efficient and effective.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Revamping Skills in Deep Agents

待翻譯:What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:LangChain just released new capabilities in Managed Deep Agents. Agents can now schedule follow-ups, reconfigure themselves on every run, and react to Slack messages.

LangChain Blog來源內容 · 翻譯待補全待翻譯:What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions

待翻譯:Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Build a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions that single-shot retrieval answers poorly. Run the same query through both paths, read the trace events, and compare what each retrieval path costs.

AWS Machine Learning Blog來源內容 · 翻譯待補全待翻譯:Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases

待翻譯:How to Build a Model Router in the Harness

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:How we built a model router into Open SWE's harness that cut median cost per coding task by 64% with no measurable drop in quality, and how to build your own.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How to Build a Model Router in the Harness

待翻譯:Building Production Agents with Jev and LangGraph

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:See how LangGraph orchestrates Jev, TypeSafe AI's decision model, to build faster, cheaper production agents.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Building Production Agents with Jev and LangGraph

待翻譯:New in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and more

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:LangChain announced new updates to LangSmith. Updates include Engine v2 with red teaming and automatic testing, a new version of Managed Deep Agents, trajectories and more.

LangChain Blog來源內容 · 翻譯待補全待翻譯:New in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and more

待翻譯:LangSmith Custom Apps: Build custom interfaces around your agent data

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:LangSmith Custom Apps lets you build the interface you want with your LangSmith data, publish it into your workspace, and skip the hosting, auth, and permissions work. Learn more.

LangChain Blog來源內容 · 翻譯待補全待翻譯:LangSmith Custom Apps: Build custom interfaces around your agent data

待翻譯:Introducing LangSmith Fine-Tuning

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:LangChain introduces LangSmith Fine-Tuning and SmithTune, a CLI built for post-training models. Train specialized models without building data pipelines by hand.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Introducing LangSmith Fine-Tuning

待翻譯:Trajectories now in LangSmith: A readable view of every agent session

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Trajectories in LangSmith provide a conversational view of an agent session. Trajectories make trace data easy to navigate and speed up debugging for long-running agents.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Trajectories now in LangSmith: A readable view of every agent session

待翻譯:New in LangSmith Engine: red teaming and automated testing

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:LangSmith Engine now includes Red Teaming to proactively detect agent issues and automated agent testing. Learn more about the Engine v2 release.

LangChain Blog來源內容 · 翻譯待補全待翻譯:New in LangSmith Engine: red teaming and automated testing

待翻譯:Managed Deep Agents delivers a better user experience for agents in production

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Managed Deep Agents is the simplest way to build, deploy, and run agents in production. The 0.8 release adds support for user-owned credentials, user-level memory, HTTP channels, file transfer in Slack and a pre-built tool for web search.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Managed Deep Agents delivers a better user experience for agents in production

待翻譯:The Reliability Layer for Healthcare AI: Common LangSmith Use Cases

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:See how LangSmith helps healthcare AI teams turn clinical review into reusable evaluators, datasets, and release gates for safer AI in production.

LangChain Blog來源內容 · 翻譯待補全待翻譯:The Reliability Layer for Healthcare AI: Common LangSmith Use Cases

待翻譯:Jev-as-a-Judge Is Now Available in LangSmith

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Use Jev as a judge for LangSmith evals to evaluate agent traces with faster, cheaper structured feedback across production runs, datasets, and regression tests.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Jev-as-a-Judge Is Now Available in LangSmith

待翻譯:Can Jev Be a Better Agent Evaluator?

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Can Jev Be a Better Agent Evaluator?

待翻譯:Building a Harness with Jev

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Open Source Agent Architecture LangChain Building a Harness with Jev September 17, 2026 5 min Go back to blog Create agents Agents run in a loop: an LLM decides what to do, a tool executes, a model evaluates the results…

LangChain Blog來源內容 · 翻譯待補全待翻譯:Building a Harness with Jev

待翻譯:Building an Agent Harness for Life Sciences: Introducing Deep Life Sci

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Deep Life Sci is LangChain's open source agentic assistant for clinical and lab scientists. It pulls from 600K+ ClinicalTrials.gov studies, 29M PubMed abstracts, and 12M PubMed Central full-text articles, with sandboxed sub-agents for real data analysis.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Building an Agent Harness for Life Sciences: Introducing Deep Life Sci

待翻譯:How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:See how Included Health used Deep Agents, LangGraph, and LangSmith to build Dot, a federated healthcare navigation agent with human handoff and clinical oversight.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents

待翻譯:Optimizing cost and latency with Amazon Bedrock prompt caching

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Prompt caching in Amazon Bedrock can cut input token costs by up to 90% when you repeatedly send the same context to foundation models. This post walks through six practical prompt caching scenarios using the Converse API: message content, system prompt, tool definition, mixed TTL, tenant isolation, and LangChain integration.

AWS Machine Learning Blog來源內容 · 翻譯待補全待翻譯:Optimizing cost and latency with Amazon Bedrock prompt caching

待翻譯:Scaling Agents in Healthcare & Life Sciences: Lessons from Madrigal Pharmaceuticals, Abridge, and Vizient

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Agent programs in healthcare and life sciences are being built under a different set of constraints than those in most industries. There’s plenty of upside if the constraints can be resolved. Success can mean hours of manual review compressed into minutes, data spread across a dozen systems finally queryable in one place, and clinicians getting time back from documentation. At the same time, the cost of a wrong answer can be higher here than almost anywhere else, which changes how teams build.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Scaling Agents in Healthcare & Life Sciences: Lessons from Madrigal Pharmaceuticals, Abridge, and Vizient

待翻譯:How We Built LangChain’s Paid Media Agent

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:How LangChain built a paid media agent to analyze campaign performance, optimize ads, propose changes, and turn marketing data into action.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How We Built LangChain’s Paid Media Agent

待翻譯:AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Pizza Bot is an open source, self-hosted inbox for AI agents built on DeepAgents and LangGraph. It combines persistent task state, MCP integrations, configurable approvals, and scheduled workflows across multiple model providers. The post AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents appeared first on MarkTechPost.

MarkTechPost來源內容 · 翻譯待補全待翻譯:AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents

待翻譯:Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:A shallow agent is an LLM calling tools in a loop, and on long tasks it fails in 2 ways: context overflow and goal loss. This article opens the harness layer that fixes both, with the actual thresholds shipped by LangChain Deep Agents, Claude Code, Manus, OpenAI Codex and Amazon Bedrock AgentCore, plus an interactive simulator that shows a 200K window filling up. The post Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks appeared first on MarkTechPost.

MarkTechPost來源內容 · 翻譯待補全待翻譯:Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

待翻譯:How Credit Genie keeps codebase docs fresh with OpenWiki

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:See how Credit Genie uses OpenWiki to automate repo documentation, reduce tribal knowledge, and give engineers and coding agents searchable codebase context.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How Credit Genie keeps codebase docs fresh with OpenWiki

待翻譯:Agentic AI-enabled Semantic Commissioning of a Cognitive Digital Twin for Reconfigurable Manufacturing

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:arXiv:2609.09503v1 Announce Type: new Abstract: Rapid bespoke commissioning of the Cognitive Digital Twin (CDT) is a major challenge in reconfigurable manufacturing. Traditional digital twin (DT) construction methods primarily focus on geometric reconstruction, often neglecting the deep semantic integration and functional interoperability necessary for autonomous reasoning. This paper proposes an agent-based, AI-driven workflow to automate end-to-end CDT debugging. The system utilises LangGraph as a multi-agent orchestration engine to achieve dual-path synthesis: the semantic path extracts technical specifications from unstructured documents using Retrieval Augmented Generation (RAG), while the functional path autonomously discovers and binds to real-time indus…

arXiv Robotics來源內容 · 翻譯待補全待翻譯:Agentic AI-enabled Semantic Commissioning of a Cognitive Digital Twin for Reconfigurable Manufacturing

待翻譯:Connections: managed credentials and per-caller identity for Managed Deep Agents

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Learn how Connections in Managed Deep Agents securely manage credentials, support per-user OAuth, and let agents act with each caller’s identity.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Connections: managed credentials and per-caller identity for Managed Deep Agents

多智慧體框架中的上下文組織

deepagents 為子代理引入“上下文模式”(isolated / fork),讓主管代理既可以委派任務,又可以決定子代理繼承多少上下文。fork 模式繼承主管的會話歷史,可複用 prompt caching、減少重複工作;isolated 模式則讓子代理在全新上下文中獨立完成任務。文章還透過 worker、verifier、researcher、memory 四類子代理說明如何選擇。

LangChain Blog站內正文多智慧體框架中的上下文組織

待翻譯:90 days of attacks on AI infrastructure

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Wiz PricingGet a demo Get a demo Wiz Threat Research operates honeypots across AI and ML services including LiteLLM, Flowise, LangChain, Langflow, ChromaDB, Ollama, and others. Over 90 days of telemetry, we observed sus…

Hacker News AI來源內容 · 翻譯待補全待翻譯:90 days of attacks on AI infrastructure

待翻譯:August 2026: LangChain Newsletter — Managed Deep Agents, LLM Gateway, and More

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Managed Deep Agents and LLM Gateway hit public beta, plus Deep Agents v0.7, Tuned Evaluators, Bring Your Own Cloud on AWS, and LangSmith Engine upgrades.

LangChain Blog來源內容 · 翻譯待補全待翻譯:August 2026: LangChain Newsletter — Managed Deep Agents, LLM Gateway, and More

待翻譯:Evaluate any agent framework with Amazon Bedrock AgentCore Evaluations

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Amazon Bedrock AgentCore Evaluations decouples agent evaluation from the framework you build on. As long as your agent emits OpenTelemetry telemetry, the service can score it, whether you use LangGraph, LlamaIndex, the OpenAI Agents SDK, Google ADK, the Claude Agent SDK, or Strands Agents. This post explains how the framework-agnostic contract works.

AWS Machine Learning Blog來源內容 · 翻譯待補全待翻譯:Evaluate any agent framework with Amazon Bedrock AgentCore Evaluations

待翻譯:LangChain State of AI 2024 Report

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Dive into LangSmith product usage patterns that show how the AI ecosystem and the way people are building LLM apps is evolving.

LangChain Blog來源內容 · 翻譯待補全待翻譯:LangChain State of AI 2024 Report

待翻譯:LangChain's Second Birthday

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Reflections on how LangChain has evolved — including our products, ecosystem, and community — over the past two years, and where we're headed next.

LangChain Blog來源內容 · 翻譯待補全待翻譯:LangChain's Second Birthday

待翻譯:How Podium optimized agent behavior and reduced engineering intervention by 90% with LangSmith

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:See how Podium tests across the lifecycle development of their AI employee agent, using LangSmith for dataset curation and finetuning. They improved agent F1 response quality to 98% and reduced the need for engineering intervention by 90%.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How Podium optimized agent behavior and reduced engineering intervention by 90% with LangSmith

待翻譯:Announcing LangGraph v0.1 & LangGraph Cloud: Running agents at scale, reliably

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Our new infrastructure for running agents at scale, LangGraph Cloud, is available in beta. We also have a new stable release of LangGraph.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Announcing LangGraph v0.1 & LangGraph Cloud: Running agents at scale, reliably

待翻譯:LangChain Announces Enterprise Agentic AI Platform Built with NVIDIA

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Build, deploy, and monitor production-grade AI agents at scale with LangChain's enterprise agentic AI platform integrated with NVIDIA.

LangChain Blog來源內容 · 翻譯待補全待翻譯:LangChain Announces Enterprise Agentic AI Platform Built with NVIDIA

待翻譯:AI Agent Latency 101: How do I speed up my AI agent?

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Learn proven strategies to speed up your AI agent: reduce latency, optimize LLM calls, enable parallelism, and improve UX. Expert tips from LangChain.

LangChain Blog來源內容 · 翻譯待補全待翻譯:AI Agent Latency 101: How do I speed up my AI agent?

待翻譯:LangChain raises $125M to build the platform for agent engineering

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:We raised $125M at a $1.25B valuation to build the platform for agent engineering.

LangChain Blog來源內容 · 翻譯待補全待翻譯:LangChain raises $125M to build the platform for agent engineering

待翻譯:Evaluating OpenWiki with WikiBench

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:We built WikiBench to test whether generated wikis help coding agents. Pairing a wiki with source code scored higher than source alone, at lower cost.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Evaluating OpenWiki with WikiBench

待翻譯:OpenAI's Bet on a Cognitive Architecture

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Why LangChain believes in open, customizable cognitive architectures over closed systems. Build reliable LLM agents with OpenGPTs and LangSmith.

LangChain Blog來源內容 · 翻譯待補全待翻譯:OpenAI's Bet on a Cognitive Architecture

待翻譯:Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Discover Connery: open-source plugin infrastructure for LLM apps. Secure integrations, personalization, and human-in-the-loop control for AI agents.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps

待翻譯:Qdrant x LangChain: Endgame Performance

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Qdrant and LangChain deliver production-ready RAG performance with async support, optimized resource usage, and scalable vector search for LLM apps.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Qdrant x LangChain: Endgame Performance

待翻譯:Data-Driven Characters

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Data-driven-characters is a repo for creating, debugging, and interacting your own chatbots conditioned on your own story corpora.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Data-Driven Characters

待翻譯:Eden AI x LangChain: Harnessing LLMs, Embeddings, and AI

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Access multiple LLMs, embeddings, and AI tools through Eden AI's LangChain integration. Unified API for text generation, OCR, speech-to-text, and more.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Eden AI x LangChain: Harnessing LLMs, Embeddings, and AI

待翻譯:LangChain State of AI 2023

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Discover how developers build LLM applications in 2023. Insights on popular models, vectorstores, retrieval strategies, and testing methods from LangSmith.

LangChain Blog來源內容 · 翻譯待補全待翻譯:LangChain State of AI 2023

待翻譯:How to design an Agent for Production

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Build production-ready AI agents with LangChain. Technical guide covering OpenAI functions, tools, prompts, and architecture for Cal.ai's scheduling assistant.

LangChain Blog來源內容 · 翻譯待補全待翻譯:How to design an Agent for Production

待翻譯:Auto-Evaluator Opportunities

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Auto-evaluate LLM question-answer chains with LangChain's free tool. Generate test sets, grade answers, and optimize chain performance.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Auto-Evaluator Opportunities

待翻譯:Applying OpenAI's RAG Strategies

AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Implement OpenAI's proven RAG strategies with LangChain. Explore query transformations, routing, post-processing, and evaluation methods for optimal retrieval.

LangChain Blog來源內容 · 翻譯待補全待翻譯:Applying OpenAI's RAG Strategies

公司導航