researchactive
ReAct: Synergizing Reasoning and Acting in Language Models
Shunyu Yao et al.
View original resourceYao et al. introduce the ReAct prompting framework that interleaves chain-of-thought reasoning traces with tool actions, letting models plan, act, and observe in a loop. Evaluated on HotpotQA, FEVER, ALFWorld, and WebShop.
Tags
agentic AIfoundations
At a glance
Published
2023
Jurisdiction
International
Category
Foundations
Access
Public access
Build your AI governance program
VerifyWise helps you implement AI governance frameworks, track compliance, and manage risk across your AI systems.