Agents 2.0: From Shallow Loops to Deep Agents

Agent "architecture" is a quickly moving topic and the state of the art is changing quick, but this approach to making more complex agents is a good example.

Moving from Shallow Agents to Deep Agents (Agent 1.0 to Agent 2.0) isn't just about connecting an LLM to more tools. It is a shift from reactive loops to proactive architecture. It is about better engineering around the model.

Implementing explicit planning, hierarchical delegation via sub-agents, and persistent memory, allow us to control the context and by controlling the context, we control the complexity, unlocking the ability to solve problems that take hours or days, not just seconds.

This space will see a ton of experimentation.