You can now run recursive language model (RLM) workflows in Deep Agents. Everything you need to know in 6 minutes from @sydneyrunkle.

Recursive Language Model (RLM) workflows are now available as a feature in Deep Agents, allowing AI systems to iteratively call language models within multi-step processes. This capability enables more complex reasoning and problem-solving by allowing language models to recursively process information and refine outputs through multiple iterations. The feature was introduced by Sydney Runkle in a 6-minute explanation shared by the LangChain team.

Source: Harrison Chase (X) | 2026-07-01