Definition
ReAct, short for Reasoning and Acting, is a prompting paradigm introduced in the 2022 paper ReAct: Synergizing Reasoning and Acting in Language Models by Yao and colleagues. It instructs a language model to generate verbal reasoning traces and concrete actions in an interleaved sequence. The model articulates a thought, takes an action such as querying a tool or external API, observes the result, then reasons again. This loop lets it build, maintain, and adjust a plan while incorporating fresh information from its environment.
Why it matters
Before ReAct, prompting techniques tended to separate pure reasoning (chain-of-thought) from acting. By fusing the two, ReAct lets a model verify intermediate claims against real data, which reduces certain hallucinations and supports multi-step tasks like question answering with a search tool. The original paper evaluated the approach on benchmarks including HotPotQA, Fever, ALFWorld, and WebShop. ReAct became a foundational building block for later autonomous-agent systems.
In modern frameworks
The ReAct loop underpins the agent designs in many of the orchestration frameworks builders use today. Understanding it helps explain why an agent emits visible thought-then-action steps and why tool access is so central to agent reliability. It is a conceptual pattern rather than a product, so it carries no license or vendor and can be implemented in any stack.
For frameworks that operationalize this pattern, see D-Central's neutral entries on LangGraph and AutoGen.
In Simple Terms
ReAct, short for Reasoning and Acting, is a prompting paradigm introduced in the 2022 paper ReAct: Synergizing Reasoning and Acting in Language Models by Yao…