Skip to content
EVENT / TOPICActive

LangChain Launches Async Sub-Agent Feature for Deep Agents

1 reports1 sources11/5/2026 updated

Current overview (not historical)

AI overview

LangChain has introduced asynchronous sub-agents for Deep Agents. The orchestrator remains available to chat with users, while sub-agents run independently in the background and report results. Five tools are provided, including start_async_task and check_async_task, and users can interrupt or queue updates to running tasks. The design lets background work proceed without blocking user interaction. The capability is available in the Python version, the JavaScript version, and the hosted platform. Task notifications are still in testing, so the API may change.

Written with AI from the reporting · updated 11/5/2026

Latest developmentNov 6, 04:03
LangChain Launches Async Subagents for Deep Agents to Enable Background Parallel Tasks
Explore the timeline, relations and evidence
Expand the detailed fact route and sources

Story route

A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.

  1. 1Unclassified fact stationNov 6, 04:04single sourcereport-time onlyrevised

    LangChain 发布 Deep Agents 异步子代理功能

    Read original source ↗ LangChain BlogReplay this moment in the explorer
    Evidence & revisions · 1 source records
    Subject：
    LangChain
    Action：
    发布异步子代理功能
    Object：
    Deep Agents
    Occurred (fact side)：
    not recorded
    LangChain Blog ↗Report pageRevision 2 · currently revised
    Published (valid side)：
    Nov 6, 04:03
    First seen (known side)：
    Nov 6, 04:04
    Fact stationSingle source · one-sided claimRevisedReport-time only

    Copy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.

Uncertainty marks flag where to check the sources; they are not proven causation.

Report timeline

Explore every side through dated source reports.

Nov 6
  1. LangChain BlogRelated fact: single sourceFact occurrence time unverifiedSource report revised
    LangChain Launches Async Subagents for Deep Agents to Enable Background Parallel Tasks

    Report first recorded Nov 6, 04:04

    LangChain announced async subagents for Deep Agents, letting an orchestrator stay available to users while background workers run tasks in parallel. The system provides five tools to start, check, update, cancel, and list async tasks, with interrupt or enqueue update strategies. It is available in Deep Agents for Python and JavaScript and Managed Deep Agents, while task notifications remain in beta.

    Read original source ↗

Event activity trend

Not enough continuous observations to chart activity.

Event discussion

Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.

Open GitHub Discussions