ReAct: Synergizing Reasoning and Acting in Language Models
Source
arxiv.org
Author
Shunyu Yao et al.
Date
Why it matters
This is the loop nearly every AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → framework implements: think, act, observe, repeat. Interleaving reasoning with tool calls cuts hallucinationWhen a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.Full definition → because the model checks itself against an external source mid-task, and it leaves a trace you can actually debug.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
hallucination — When a model states something false with full confidence — inventing facts, citations, or APIs that don't exist.
articleCoupling Planning with Episodic Memory in LLM Agents for Software Issue ResolutionJiahao Zhang, Yifan Zhang, Yu Huang
articleLanguage Models Don T Always Say What They Think Unfaithful Explanations In Chain Of Thought Prompting 2023 05 07Cohere
articleAdaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scalingbair.berkeley.edu