# ReAct pattern

**Source:** https://promtable.com/glossary/react-pattern

> ReAct interleaves Reasoning + Acting in an agent loop — the model writes a thought, then decides to call a tool, then observes the result, then thinks again.

---
ReAct interleaves Reasoning + Acting in an agent loop — the model writes a thought, then decides to call a tool, then observes the result, then thinks again.

ReAct (Yao et al., 2022) was the original recipe for LLM agents. Each step has three parts: Thought (free-form reasoning), Action (tool call), Observation (tool result fed back in). The loop continues until the model emits a Final Answer. Modern agent frameworks (LangGraph, OpenAI Agents SDK, Claude Agent SDK) all implement variations of ReAct, often with a planner that pre-decomposes the task before the executor loop begins. Pure ReAct can drift on long horizons — add budget caps and a planner-executor split for reliability.

## When to use

- Agents with tools where each step depends on the previous result.
- Web research, code editing, browser automation.

## Common mistakes

- Letting the loop run unbounded — set a max step count.
- Pure ReAct on tasks with branching planning needs — use a planner first.

## Related terms

- [agent](https://promtable.com/glossary/agent)
- [function-calling](https://promtable.com/glossary/function-calling)
- [chain-of-thought](https://promtable.com/glossary/chain-of-thought)

## Sources

- [Yao et al. 2022 (arXiv)](https://arxiv.org/abs/2210.03629)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/react-pattern
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/react-pattern".
Contact: info@vibecodingturkey.com.