ReAct (Reason + Act)
Also known as: Reason and Act, ReAct pattern
Agent loop pattern: Thought → Action → Observation → Thought → … until the task is done.
An agent prompting pattern that interleaves reasoning (Thought) with tool calls (Action) and observations (Observation) in a loop. Predecessor to most modern function-calling agent loops.
In practice
The classical agent loop everyone reinvents. Knowing it makes function calling, tool use, and agent frameworks click instantly.
How it compares
ReAct is one specific reasoning pattern for agents; agents is the broader category of LLM-driven systems.
Comparisons that include ReAct (Reason + Act)
Related topics
Related terms
Prompt Engineering
Crafting the input text so the model produces the behavior you want.
AI Agents
LLMs that loop: plan → call tools → observe results → repeat until done.
Model Context Protocol (MCP)
An open protocol (from Anthropic) for letting LLMs call tools and read resources from any compatible server.
Chain-of-Thought (CoT)
Ask the model to think step by step before answering. It boosts accuracy on reasoning tasks.
In-Context Learning (ICL)
Show the model a few examples in the prompt and it learns the pattern, no fine-tuning needed.
Function Calling
The model emits structured JSON specifying a tool call instead of free text; the host executes it.