Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, “Manus”, and “Claude Code” have gotten around this limitation by implementing a combination of four things: a planning tool, sub agents, access to a file system, and a detailed prompt.
Deep Agents are agents that use these four things to execute on longer time horizon tasks.
Blog: https://blog.langchain.com/deep-agents/
GitHub: https://github.com/hwchase17/deepagents
Learn to build Deep Agents on LangChain Academy: https://academy.langchain.com/courses/deep-agents-with-langgraph/?utm_medium=social&utm_source=youtube&utm_campaign=q4-2025_youtube-academy-links_aw
Observe, evaluate, and deploy agents with LangSmith: https://smith.langchain.com/?utm_medium=social&utm_source=youtube&utm_campaign=q4-2025_youtube-links_aw
