Unverified50% confidenceFactExact time
微软的AutoGen框架和斯坦福的Generative Agents论文（Smallville实验，让25个Agent模拟人类社会行为）是多智能体系统方向的标志性工作
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
AI Agent开发全解析：智能体赛道机遇与入门路径
bilibili大模型Agent开发7/9/2026
Related Claims
Unverified斯坦福2023年「虚拟小镇」（Generative Agents）实验以25个 GPT-4 实例模拟社会行为，展示了 LLM 多智能体的涌现协作能力79% similarVerified斯坦福的Smallville虚拟社会实验让25个Agent模拟小镇居民互动，揭示了多Agent协作中涌现类社会行为的可能性77% similarPartially Verified斯坦福大学2023年发布的「Generative Agents」论文展示了25个LLM Agent在虚拟环境中自发涌现社交行为76% similarUnverified斯坦福大学的'生成式智能体'（Generative Agents）实验和AutoGPT项目的爆火，标志着Agent从学术概念进入大众视野74% similarUnverifiedSince 2023, projects like Stanford's Generative Agents, Microsoft's AutoGen, and Andrew Ng's Agentic Workflow have demonstrated that LLM-based agents can handle complex cognitive tasks including planning, execution, and reflection74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/486428API
curl https://kongchang.com/api/v1/knowledge/claims/486428MCP
get_claim(id=486428)