Shunyu Yao
AI researcher and lead author of the ReAct paper. His research focuses on agent framework design for language models interacting with external environments, exploring how language models can combine reasoning and acting to solve complex tasks by leveraging external tools and knowledge sources.
Core Facts
Timeline (last 90 days)
The ReAct pattern is short for "Reasoning + Acting" and was proposed by Shunyu Yao and others in a 2022 paper.
The ReAct paper, published at ICLR 2023 by Shunyu Yao et al., proposes that thought does not alter the environment and therefore does not produce an observation.
2023年Yao等人提出的ReAct范式让模型交替进行思考（Thought）和行动（Action），奠定了现代Agent的基本工作模式
ReAct范式由普林斯顿大学的Shunyu Yao等人在论文《ReAct: Synergizing Reasoning and Acting in Language Models》中提出，该论文于2022年10月发表并被ICLR 2023收录
All Facts (5)
The ReAct framework was published at NeurIPS in 2022 by Yao et al., demonstrating that interleaving natural language reasoning traces with action steps significantly outperforms using chain-of-thought alone or action sequences alone.
80%UnverifiedThe ReAct pattern is short for "Reasoning + Acting" and was proposed by Shunyu Yao and others in a 2022 paper.
50%UnverifiedThe ReAct paper, published at ICLR 2023 by Shunyu Yao et al., proposes that thought does not alter the environment and therefore does not produce an observation.
50%Unverified2023年Yao等人提出的ReAct范式让模型交替进行思考（Thought）和行动（Action），奠定了现代Agent的基本工作模式
50%UnverifiedReAct范式由普林斯顿大学的Shunyu Yao等人在论文《ReAct: Synergizing Reasoning and Acting in Language Models》中提出，该论文于2022年10月发表并被ICLR 2023收录
50%