ReAct Pattern
An agent architecture that interleaves Reasoning and Acting steps, where the model thinks about what to do next, takes an action, observes the result, and repeats. ReAct combines chain-of-thought reasoning with tool use in a unified loop.
The ReAct pattern (Reason + Act) is one of the most widely adopted agent architectures. At each step, the agent generates a thought explaining its reasoning, decides on an action to take, executes that action, and observes the result. This cycle continues until the task is complete. The explicit reasoning traces make the agent's decision-making transparent and debuggable.
For teams building production agents, ReAct provides a good balance of capability and observability. The reasoning steps create natural audit logs that help you understand why an agent took a particular path, which is invaluable for debugging and improving agent behavior. The pattern works well for tasks that require dynamic tool selection, like customer support agents that need to check orders, process refunds, or escalate issues based on context. Most agent frameworks including LangChain and LlamaIndex implement ReAct as a default agent type.
Related Terms
Model Context Protocol (MCP)
An open standard that defines how AI models connect to external tools, data sources, and services through a unified interface. MCP enables agents to dynamically discover and invoke capabilities without hardcoded integrations.
Tool Use
The ability of an AI model to invoke external functions, APIs, or services during a conversation to perform actions beyond text generation. Tool use transforms language models from passive responders into active problem solvers.
Function Calling
A model capability where the AI generates structured JSON arguments for predefined functions rather than free-form text. Function calling provides a reliable bridge between natural language understanding and programmatic execution.
Agentic Workflow
A multi-step process where an AI agent autonomously plans, executes, and iterates on tasks using tools, reasoning, and feedback loops. Agentic workflows go beyond single-turn interactions to accomplish complex goals.
Chain of Thought
A prompting technique that instructs the model to break down complex problems into sequential reasoning steps before producing a final answer. Chain of thought significantly improves accuracy on math, logic, and multi-step tasks.
Tree of Thought
An advanced reasoning framework where the model explores multiple solution paths simultaneously, evaluates each branch, and selects the most promising approach. Tree of thought enables more thorough problem-solving than linear chain-of-thought reasoning.