Unverified50% confidenceFactExact time
ReAct由Yao et al.于2022年提出，将推理链与外部环境交互交织形成Thought→Action→Observation的迭代循环
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
VerifiedThe ReAct (Reasoning + Acting) framework was proposed by Yao et al. in 2022, alternating Chain-of-Thought reasoning with external tool interactions.82% similarUnverifiedThe 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.77% similarVerifiedThe ReAct framework was proposed by a Princeton University team in 2022; its core idea is to have large language models alternately perform thinking and action, incorporating environmental feedback into the next round of reasoning to form a closed loop.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/516355API
curl https://kongchang.com/api/v1/knowledge/claims/516355MCP
get_claim(id=516355)