Agents are going async: Deep Agents adds background subagents
The point
LangChain is bringing async subagents to Deep Agents. An orchestrator stays available to the user while subagents run in the background and report back when done. It manages them with five tools: start, check, update, cancel, and list.
Why it matters
For builders, capacity grows with added background workers instead of one blocking loop.
Key details
- Available in Deep Agents for Python and JavaScript, and in Managed Deep Agents
- Making a subagent async in Managed Deep Agents takes one field
- Task notifications are in beta, so the API may still change
Original ~5 min → 25 sec here Source: LangChain Blog, Nov 5, 2026