跳到主要内容
AI News HubLIVE

来源分布

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

主题分布

  • Agent50
  • 研究31
  • 模型18
  • 创业融资5

日期线

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

最新动态

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:How to build great out-of-the-box user experiences with Managed Deep Agents

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Discover how Snyk transformed an internal support agent into Snyk Assist, a customer-facing AI feature powered by LangChain, LangGraph, and LangSmith.

LangChain Blog来源内容 · 翻译待补全待翻译:How Snyk Turned an Internal Support Agent into a Customer Feature

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Agents that can pay: building Restock with Stripe's Link and Managed Deep Agents

待翻译:Revamping Skills in Deep Agents

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Revamping Skills in Deep Agents

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:How to Build a Model Router in the Harness

待翻译:Building Production Agents with Jev and LangGraph

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:See how LangGraph orchestrates Jev, TypeSafe AI's decision model, to build faster, cheaper production agents.

LangChain Blog来源内容 · 翻译待补全待翻译:Building Production Agents with Jev and LangGraph

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:New in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and more

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:LangSmith Custom Apps: Build custom interfaces around your agent data

待翻译:Introducing LangSmith Fine-Tuning

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Introducing LangSmith Fine-Tuning

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Trajectories now in LangSmith: A readable view of every agent session

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:LangSmith Engine now includes Red Teaming to proactively detect agent issues and automated agent testing. Learn more about the Engine v2 release.

LangChain Blog来源内容 · 翻译待补全待翻译:New in LangSmith Engine: red teaming and automated testing

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Managed Deep Agents delivers a better user experience for agents in production

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:See how LangSmith helps healthcare AI teams turn clinical review into reusable evaluators, datasets, and release gates for safer AI in production.

LangChain Blog来源内容 · 翻译待补全待翻译:The Reliability Layer for Healthcare AI: Common LangSmith Use Cases

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Jev-as-a-Judge Is Now Available in LangSmith

待翻译:Can Jev Be a Better Agent Evaluator?

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Can Jev Be a Better Agent Evaluator?

待翻译:Building a Harness with Jev

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Building a Harness with Jev

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Building an Agent Harness for Life Sciences: Introducing Deep Life Sci

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Optimizing cost and latency with Amazon Bedrock prompt caching

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Scaling Agents in Healthcare & Life Sciences: Lessons from Madrigal Pharmaceuticals, Abridge, and Vizient

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:How LangChain built a paid media agent to analyze campaign performance, optimize ads, propose changes, and turn marketing data into action.

LangChain Blog来源内容 · 翻译待补全待翻译:How We Built LangChain’s Paid Media Agent

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:See how Credit Genie uses OpenWiki to automate repo documentation, reduce tribal knowledge, and give engineers and coding agents searchable codebase context.

LangChain Blog来源内容 · 翻译待补全待翻译:How Credit Genie keeps codebase docs fresh with OpenWiki

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Agentic AI-enabled Semantic Commissioning of a Cognitive Digital Twin for Reconfigurable Manufacturing

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Connections: managed credentials and per-caller identity for Managed Deep Agents

多智能体框架中的上下文组织

deepagents 为子代理引入“上下文模式”(isolated / fork),让主管代理既可以委派任务,又可以决定子代理继承多少上下文。fork 模式继承主管的会话历史,可复用 prompt caching、减少重复工作;isolated 模式则让子代理在全新上下文中独立完成任务。文章还通过 worker、verifier、researcher、memory 四类子代理说明如何选择。

LangChain Blog站内正文多智能体框架中的上下文组织

待翻译:90 days of attacks on AI infrastructure

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:90 days of attacks on AI infrastructure

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:August 2026: LangChain Newsletter — Managed Deep Agents, LLM Gateway, and More

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Evaluate any agent framework with Amazon Bedrock AgentCore Evaluations

待翻译:LangChain State of AI 2024 Report

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Dive into LangSmith product usage patterns that show how the AI ecosystem and the way people are building LLM apps is evolving.

LangChain Blog来源内容 · 翻译待补全待翻译:LangChain State of AI 2024 Report

待翻译:LangChain's Second Birthday

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:LangChain's Second Birthday

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:How Podium optimized agent behavior and reduced engineering intervention by 90% with LangSmith

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Announcing LangGraph v0.1 & LangGraph Cloud: Running agents at scale, reliably

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Build, deploy, and monitor production-grade AI agents at scale with LangChain's enterprise agentic AI platform integrated with NVIDIA.

LangChain Blog来源内容 · 翻译待补全待翻译:LangChain Announces Enterprise Agentic AI Platform Built with NVIDIA

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:AI Agent Latency 101: How do I speed up my AI agent?

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:We raised $125M at a $1.25B valuation to build the platform for agent engineering.

LangChain Blog来源内容 · 翻译待补全待翻译:LangChain raises $125M to build the platform for agent engineering

待翻译:Evaluating OpenWiki with WikiBench

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Evaluating OpenWiki with WikiBench

待翻译:OpenAI's Bet on a Cognitive Architecture

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Why LangChain believes in open, customizable cognitive architectures over closed systems. Build reliable LLM agents with OpenGPTs and LangSmith.

LangChain Blog来源内容 · 翻译待补全待翻译:OpenAI's Bet on a Cognitive Architecture

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Discover Connery: open-source plugin infrastructure for LLM apps. Secure integrations, personalization, and human-in-the-loop control for AI agents.

LangChain Blog来源内容 · 翻译待补全待翻译:Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps

待翻译:Qdrant x LangChain: Endgame Performance

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Qdrant and LangChain deliver production-ready RAG performance with async support, optimized resource usage, and scalable vector search for LLM apps.

LangChain Blog来源内容 · 翻译待补全待翻译:Qdrant x LangChain: Endgame Performance

待翻译:Data-Driven Characters

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Data-driven-characters is a repo for creating, debugging, and interacting your own chatbots conditioned on your own story corpora.

LangChain Blog来源内容 · 翻译待补全待翻译:Data-Driven Characters

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

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译: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来源内容 · 翻译待补全待翻译:Eden AI x LangChain: Harnessing LLMs, Embeddings, and AI

待翻译:LangChain State of AI 2023

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Discover how developers build LLM applications in 2023. Insights on popular models, vectorstores, retrieval strategies, and testing methods from LangSmith.

LangChain Blog来源内容 · 翻译待补全待翻译:LangChain State of AI 2023

待翻译:How to design an Agent for Production

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Build production-ready AI agents with LangChain. Technical guide covering OpenAI functions, tools, prompts, and architecture for Cal.ai's scheduling assistant.

LangChain Blog来源内容 · 翻译待补全待翻译:How to design an Agent for Production

待翻译:Auto-Evaluator Opportunities

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Auto-evaluate LLM question-answer chains with LangChain's free tool. Generate test sets, grade answers, and optimize chain performance.

LangChain Blog来源内容 · 翻译待补全待翻译:Auto-Evaluator Opportunities

待翻译:Applying OpenAI's RAG Strategies

AI 服务暂时不可用,以下为来源摘要,待恢复后补全翻译:Implement OpenAI's proven RAG strategies with LangChain. Explore query transformations, routing, post-processing, and evaluation methods for optimal retrieval.

LangChain Blog来源内容 · 翻译待补全待翻译:Applying OpenAI's RAG Strategies

公司导航