AI Glossary

ReAct (Reason + Act)

ReAct is an agent execution pattern in which a model alternates between reasoning about a task and taking an action, such as firing a query or calling a tool, repeating the cycle until it decides it has an answer.

Also known as: reason and act, reasoning and acting

· Updated · Chain of Thought

AI Agents

The name comes from the 2022 paper ReAct: Synergizing Reasoning and Acting in Language Models by Yao and colleagues, which prompts a model to generate reasoning traces and task actions in an interleaved way: the reasoning tracks and updates the plan, and the actions let it work with external sources, such as a knowledge base or an environment.

In a ReAct loop, an agent doesn’t plan its full approach up front; it reasons about what to do next, takes one action, observes the result, and reasons again. This makes agents adaptive, but it also means an agent with incomplete context can get stuck repeatedly firing queries against data it doesn’t actually have access to, unable to reason its way to ‘I can’t answer this.’

The pattern is one driver behind the surge in query volume data platforms have seen as agents come online — agents in a reason-act loop can generate far more requests, far faster, than a human ever would, including unbounded or wasted queries when they lack the context to recognize a dead end.

ReAct: reason, act, observe, repeat Left: the ReAct loop. The model reasons about what to do next, acts by calling a tool or firing a query, observes the result, and reasons again, leaving the loop when it decides it has an answer. Right: the same loop without the context it needs. It reasons, fires a query, gets nothing useful, and fires another, so query volume climbs and the loop may never reach the conclusion that it cannot answer. Below: the pattern comes from the 2022 ReAct paper by Yao and colleagues; Starburst's Jitender Aswani described the runaway version in episode 66. ReAct: one step at a time The agent doesn’t plan everything up front. It thinks, acts once, looks at the result, and thinks again. THE LOOP Reason what should I do next? Act call a tool, run a query Observe read the result answer It leaves the loop when it decides it has an answer. WITHOUT THE RIGHT CONTEXT Reason Query nothing useful Reason Query nothing useful Reason Query nothing useful ⋮ Query volume climbs, and the loop may never reach “I can’t answer this.” The pattern: Yao et al., “ReAct: Synergizing Reasoning and Acting in Language Models” (2022). Reasoning tracks and updates the plan; actions reach outside sources. The runaway version: Starburst’s Jitender Aswani on agents firing queries “at insane speed,” episode 66.
The loop is from the 2022 ReAct paper by Yao and colleagues. The runaway version is how Jitender Aswani described agents hitting data platforms in episode 66. Download the image

Hear it from the guest

“They operate in this react mode, they reason, they act, they reason, they act, they are generating queries at insane speed.”
Jitender Aswani, Starburst EP 66 · around 35:36 · read the transcript

Quotes lightly edited to remove filler words.

Go deeper

From the conversation

Related terms

Tool Use (Function Calling)Agentic WorkflowAI AgentContext Poisoning