ReAct Pattern

Full definition

Introduced by Yao et al. (Princeton/Google, 2022), ReAct outperformed both chain-of-thought-only and act-only baselines on knowledge-intensive and decision-making tasks. The pattern is now the canonical agent loop in LangChain, LlamaIndex, and most agent frameworks. Modern function-calling LLMs implement ReAct natively in their tool-use training.

Why it matters

ReAct is the simplest pattern that turns a chat LLM into an agent. Understanding it is prerequisite to designing reliable agentic workflows — including knowing when ReAct's chattiness is excessive overhead and a planner-executor split would be cheaper.

Example

Thought: "I need yesterday's closing price." Action: get_stock_price("AAPL", "2026-05-01"). Observation: 224.18. Thought: "Now I can compute the daily change."

Related terms

• Chain-of-Thought (CoT)
  Chain-of-Thought (CoT) is a prompting and training technique in which a language model is encouraged to reason step-by-step before producing its final answer — improving accuracy on math, logic, and multi-hop reasoning by 10-40 percentage points on standard benchmarks.
• Agentic Workflow
  An agentic workflow is a multi-step AI process where a model plans, takes actions through tools, observes results, and iterates toward a goal — replacing single-shot prompting with a loop that reasons, acts, and self-corrects.
• Tool Use (LLM)
  LLM tool use (also called function calling) is the ability of a language model to invoke external functions, APIs, databases, or systems based on the user's request — turning the LLM from a text generator into a controller that can act on the world.
• AI Agent / Agentic AI
  An AI agent is an LLM-driven system that, given a goal, plans a sequence of steps, calls tools or APIs, observes the results, and iterates until the goal is reached — going beyond single-turn chat to multi-step autonomous action.