Unverified50% confidenceFactExact time
自我反思（self-reflection）由Shinn等人在2023年的Reflexion论文中系统化，该论文发表于NeurIPS 2023
1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Verification Loops Quadruple DeepSeek's Intelligence at One-Seventh the Cost of Claude Opus
hackernewshackernews7/7/2026
Related Claims
UnverifiedAnthropic研究团队2023年发表了关于奉承性偏差的系统性分析68% similarUnverifiedReflexion was proposed in 2023 by MIT and other institutions, allowing an Agent to generate verbal self-criticism after task failure and inject it into the next round of execution.61% similarUnverified线性注意力思路由 Katharopoulos 等人在 2020 年论文《Transformers are RNNs》中系统化60% similarUnverifiedThe field of mechanistic interpretability was largely founded by the Anthropic research team (especially Chris Olah) around 2021 through the "Transformer Circuits" series of papers.60% similarUnverifiedAnthropic在2023年发表了'表征工程'研究，Turner等人发表了'激活加法'工作，都是该技术范式的代表性成果59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/284407API
curl https://kongchang.com/api/v1/knowledge/claims/284407MCP
get_claim(id=284407)