ReAct Pattern

The Reasoning and Acting (ReAct) pattern is the foundational architecture where agents alternate between thinking steps and tool calls in a loop, combining chain-of-thought reasoning with grounded actions. Each cycle produces a thought (the model's reasoning about what to do next), an action (a tool call or output), and an observation (the result of the action) that feeds the next iteration; most modern agent frameworks use this pattern because the visible reasoning chain lets you understand why the agent chose a particular action without needing to instrument the model internals. Recognizing the pattern's failure modes, including unbounded loops, reasoning drift, and error compounding, is what drives the need for more constrained patterns like state machines, making ReAct the essential baseline to understand before any other architecture makes sense.