ReAct: Synergizing Reasoning and Acting in LMs

Editorial record

Plain-language summary

The method prompts a language model to alternate between writing a reasoning step and issuing an action, such as a query to a search API, then feeding the observation back before the next thought. This lets the model plan, look things up to correct itself, and reduce fabricated facts on knowledge tasks like HotpotQA and FEVER, while the reasoning traces make its behavior on interactive benchmarks more legible. It became a common template for tool-using and agentic prompting because it needs no fine-tuning, only few-shot exemplars.