LLM Digest

Story

langchain_blog · Oct 13, 2026 · news

Source brief

Building Long-Running Agents with ScaleDown and Deep Agents

the LangChain blogOct 13, 2026
original source linked

In brief

Use ScaleDown's constrained decoding models with LangChain and Deep Agents to summarize history, compress tool results, and extract data faster and cheaper.

Feed lens

agent

Read the original at langchain.com →Open in live feed

Building Long-Running Agents with ScaleDown and Deep Agents

Earlier in this thread 4 items

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

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

Revamping Skills in Deep Agents

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