ReAct
Also called Reason + Act, thought-action-observation loop.
ReAct is a prompting pattern that interleaves reasoning traces ("Thought") with actions such as tool calls ("Action") and their results ("Observation"), letting a model plan, act, and update its plan in a loop.
Description
Yao et al. showed that combining reasoning and acting outperformed either alone on question answering and interactive decision-making tasks. ReAct is the template for most tool-using agent loops.
Example
Thought: I need the population of the capital of France.
Action: search("capital of France")
Observation: Paris
Thought: Now find the population of Paris.Sources
- Yao et al. (2022). ReAct: Synergizing Reasoning and Acting in Language Models.
Cite this entry
Protologue. (2026). ReAct. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0058). https://protologue.com/t/react/
BibTeX
@misc{protologue_react,
title = {ReAct},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0058},
url = {https://protologue.com/t/react/}
}