Unverified50% confidenceFactExact time
After ReAct, the community developed variant frameworks such as Reflexion, LATS, and Plan-and-Solve.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe 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.68% similarUnverifiedReAct has evolved into multiple variants such as Plan-and-Execute, Reflexion, and Tree of Thoughts.68% similarUnverifiedReAct establishes an alternating execution protocol between reasoning traces and actions, writing observations returned by tools into the context before the next round of reasoning, laying the theoretical foundation for mainstream agent frameworks such as LangChain, AutoGPT, and Claude tool calling.67% similarUnverifiedLLM作为调度中枢的设计模式被称为ReAct（Reasoning + Acting）框架66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/894675API
curl https://kongchang.com/api/v1/knowledge/claims/894675MCP
get_claim(id=894675)