Unverified85% confidenceFactTime unknown
斯坦福大学2023年发布了Reflexion框架，通过语言反馈而非梯度更新来实现Agent的学习
1
Sources
85%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
Unverified斯坦福大学 2023 年的研究将提示词设计类比为为新员工写工作说明书72% similarUnverified斯坦福大学和微软研究院在2024年发表的多篇论文证明动态提示策略在复杂推理任务中的表现显著优于静态提示71% similarUnverifiedIn 2023, Stanford University published the paper 'Generative Agents,' marking the transition of Agents from an academic concept to engineering practice.69% 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.69% similarVerifiedThe term "foundation model" was formally introduced by Stanford University's HAI Institute in 2021.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4309API
curl https://kongchang.com/api/v1/knowledge/claims/4309MCP
get_claim(id=4309)