Partially Verified70% confidenceFactExact time
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
4
Sources
70%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
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81% similarUnverified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76% 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 reflection70% similarUnverified斯坦福大学2024年发布的Generative Agents研究验证了多步骤智能体在复杂任务分解上的有效性69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/507986API
curl https://kongchang.com/api/v1/knowledge/claims/507986MCP
get_claim(id=507986)