创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

LangChain 推出 Deep Agents 异步子代理

AI 总结

LangChain 为 Python 和 JavaScript 版 Deep Agents 推出异步子代理,并已登陆 Managed Deep Agents。该设计让面向用户的协调器保持可交互,同时由后台子代理并行执行任务并回传结果,开发者可通过工具启动、检查、更新、取消和列出任务。任务通知仍处于测试阶段,API 可能继续调整。

深度见解

这项功能让开发者能够在多个长任务并行执行时保持智能体可交互,同时解决标准 ReAct 循环中长时间工具调用阻塞后续任务的问题。

Key Takeaways

  • As agents take on bigger goals, they need to stay responsive to the user while making progress on many long tasks at once.
  • Async subagents split an agent into an orchestrator that stays available to the user and subagents that run tasks in the background and report back to the orchestrator upon completion.
  • Background work is becoming the norm for agent infrastructure, from coding agents like Claude Code to personal agents like OpenAI's dots.

Imagine a chief of staff who disappears every time you hand them a big project and only comes back once it's done. You'd probably fire them immediately. A good chief of staff keeps projects moving in the background while staying reachable and keeping you updated along the way. As we ask agents to work toward bigger goals, they need the same two properties. An agent has to be responsive, acting on a new instruction right away with the context of everything before it, and productive, making progress on many large tasks at once.

The architecture we've used to build agents for a while can't meet both requirements. In a standard ReAct loop, each long tool call blocks the loop and every other task queues behind it. Instead, we're seeing the ecosystem converge on a split between one agent that stays with the user and background workers that do the long work. Claude Code runs subagents in the background by default, OpenAI's dots hand work to background workers to make progress on several things at once, and DeepSeek Harness built its super agent around a router that talks to people and background workers that run tasks in parallel.

#LangChain#Deep Agents#Managed Deep Agents

原文约 4 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。