ReAct (reason and act)
Choose an action, use a tool, inspect the result, and repeat as needed.
The fuller definition
A prompting approach that interleaves reasoning text, tool actions, and observations to help a model solve a task.
- Plan
Select an action
- Act
Use a tool
- Observe
Use its returned result
A simplified relationship, not a screenshot or a complete design.
A concrete example
A system searches a source, inspects the returned result, and chooses another action.
The distinction that matters
The original research pattern is distinct from the React web framework. Modern agent loops need not expose internal reasoning.
Related terms
Agent loop
The cycle an agent repeats: look, decide, act, check, until the task is done or it must stop.
Agents & automationTool calling
The model asking for a tool to be run, and the application running it and handing back the result.
Agents & automationAI agent
An AI system that takes steps to do a task. It may choose tools, search, or work with files. Its access should have clear limits.
Where it is taught
Prompts, skills, workflows, and agentsSource and further reading
Yao et al. · ReAct: Synergizing Reasoning and Acting in Language Models (arXiv, October 2022)The definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.