there's a lot to be excited about with this release! * For one this solves a huge issue just generally with long-running agent UX * For two …

there's a lot to be excited about with this release! * For one this solves a huge issue just generally with long-running agent UX * For two this is a key unlock for us to go test more adaptive methods of context eng. Subagent threads being persisted, swarm-style workloads, etc. the best part - it's all out in the open for you to go break and experiment with!

langgraph persistence lets you checkpoint agent state at every step so you can pause, resume, and replay from any point. essential for long-…
Big release here! Async subagents will become more and more of a thing, as subagents get longer running and you don’t want to block the even…
tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheate…
Deep Agents deploy gets you: - Deep Agents harness - Sandbox of your choice (@daytonaio , @modal , @RunloopDev ) - Short and long term memor…
@hwchase17 Agent harnesess will simplify multi-agent orchestration and it is finally the next big thing, albeit it looks different from what…

Source: Harrison Chase (X) | 2026-04-16

Related