Skip to content

AI Glossary · Concepts

What is ReAct (Reason + Act)?

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

  • 3 explainers
  • 1 episode
  • 1 guest clip
  • 1 source

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 have to fix its full approach up front: it reasons about what to do next, takes an action, observes the result, and revises the plan. The paper also allows several actions between reasoning steps for decision-making tasks, so a thought before every single tool call is not the definition. 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.’

Starburst’s Jitender Aswani ties this loop to the surge in query volume his data platform saw as agents came online, including unbounded queries fired by agents that lacked the context to recognize a dead end, and a jump when Starburst launched its own MCP server (episode 66, 32:50). That is his account of one platform’s traffic, not a controlled comparison of agent designs.

Follow a request through the loop

An invented, read-only example: an agent is asked whether a fictional SDK’s v2 release supports batch publishing.

StepWhat happens
Reason, then actThe answer needs v2 evidence, so the agent requests the v2 release notes instead of guessing from an older version.
ObserveThe tool returns only the v1 notes. That is the wrong version, not confirmation either way.
Revise or stopThe agent tries another version-specific source within its call budget. If the evidence is still missing, it answers “unresolved” and names the gap.

The last row is the step the episode 66 agents skipped. A prompt alone does not enforce it: set a call budget and a missing-evidence exit in the application, then record requested and executed calls, repeated requests and the final answer for each test case. The ReAct paper’s own error analysis lists repeated thoughts and actions that fail to escape a loop as one failure pattern (Yao et al., section 3.3). A short trace can still be wrong, and a long one can be necessary, so judge both the answer and the calls it took.

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.”
Watch on YouTube

Quotes lightly edited to remove filler words.

Sources

Go deeper

From the conversation