Unverified50% confidenceFactExact time
早在20世纪90年代，软件代理研究已经提出了'自主感知-决策-行动'的基本框架，并在分布式计算和网络爬虫领域有所应用
1
Sources
50%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
Related Claims
Unverified自主Agent引入了工具调用和环境交互能力，能形成完整的感知-决策-执行闭环，这一范式源于2023年前后的ReAct框架及Function Calling、Tool Use等标准化接口69% 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 reflection68% similarUnverifiedMulti-Agent collaboration is essentially the automation of engineering practices validated over decades, such as code review and pair programming.68% similarUnverified科研自动化 Agent 通常基于 LLM 的工具调用与任务规划能力，结合代码执行沙箱、文件系统访问、学术检索及 GitHub/Hugging Face API 等外部工具，形成感知-规划-执行-反馈的闭环67% similarUnverified2024年出现自主编程Agent阶段，代表工具包括Devin和SWE-agent，具备自主分解任务、调用工具、运行测试、修复错误的能力67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/417178API
curl https://kongchang.com/api/v1/knowledge/claims/417178MCP
get_claim(id=417178)