Unverified50% confidenceFactExact time
现代LLM-based Agent流行架构由Yao等人在2023年的ReAct论文中奠基，将推理与行动交织在同一生成过程中
1
Sources
50%
Confidence
Long-term
Relevance
7/25/2026
First Seen
Sources
AI编程接单变现：四周学习路线的冷静拆解与真实评估
Related Claims
VerifiedThe ReAct (Reasoning + Acting) framework was proposed by Yao et al. in 2022, alternating Chain-of-Thought reasoning with external tool interactions.77% 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.74% similarUnverifiedAn LLM Agent is a modern implementation of the BDI architecture with a large language model as its 'brain,' where the model's reasoning capability serves as the engine for belief updating and intention generation.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/612046API
curl https://kongchang.com/api/v1/knowledge/claims/612046MCP
get_claim(id=612046)