What did the Yao et al. 2022 ReAct paper establish about combining reasoning and acting?

Attempt it

Your answer

Quick reference

TL;DR

ReAct showed that interleaving reasoning traces with tool actions beats reasoning alone or acting alone, and it gave agents their Thought, Action, Observation loop.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine doing a treasure hunt. One friend just thinks hard in their head about where the treasure is but never checks a single clue, so their confident guesses drift away from reality. Another friend runs around grabbing every clue but never stops to reason about what the clues mean, so they wander aimlessly. The smart approach is to do both, turn by turn: think a little about your next move, go check one clue, look at what you found, then think again with that new fact in hand. ReAct is the research that showed a language model works the same way. When it alternates between reasoning out loud and taking real actions like a search, it stays grounded in facts and plans better than doing either one on its own.

Key concepts

ReAct Pattern Chain of Thought Tool Use

Detailed answer & concept explanation

~7 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

Define ReAct and its year, lay out the three-way comparison and which condition won, explain the grounding mechanism that corrects errors turn by turn, then trace the Thought, Action, Observation loop directly onto modern function calling and agent frameworks before noting its cost limits.

Real-world examples

Real products, models, and research that use this idea.

LangGraph ships a prebuilt ReAct agent that wraps Anthropic or OpenAI function calling in a state graph, with each node running one Thought, Action, Observation turn.
Anthropic's tool use in Claude Opus 4.7 is ReAct under the hood: the model reasons, emits a typed tool call, reads the result, and continues until it answers.
OpenAI tool use with GPT-5.5 follows the same cycle, replacing ReAct's free text actions with structured JSON function calls to cut parsing errors.
Coding agents like Cursor and Aider run a ReAct style loop where the action is a file edit or test run and the observation is the diff or test output.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow does modern function calling change ReAct's original free text action format, and what problem does that solve?

Sign in or go Pro to see the approach for this follow-up.

QWhy does interleaving reasoning and acting reduce error compounding compared to planning everything up front?

Sign in or go Pro to see the approach for this follow-up.

QWhat weaknesses of plain ReAct did later methods like reflection and planning try to fix?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Calling ReAct merely a prompting trick. Its lasting contribution is the Thought, Action, Observation loop that grounds reasoning in real tool results and underpins modern agents.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.

ReAct: Synergizing Reasoning and Acting in Language Models