有效性才是你需要的
Validity Is What You Need
AI总结：
本文提出Agentic AI的现实主义定义，强调其作为应用的成功取决于用户验证而非基础模型，并指出在良好验证下可用更简单可解释的模型替代LLMs。
摘要：
尽管AI智能体在计算机科学中早已被讨论和研究，但当今的Agentic AI系统是全新的事物。我们考察了Agentic AI的其他定义，并提出了一种新的现实主义定义。Agentic AI是一种软件交付机制，类似于软件即服务（SaaS），它使应用能够自主地在复杂的企业环境中运行。近期，大型语言模型（LLMs）作为基础模型的进展推动了人们对Agentic AI的热情。然而，我们注意到Agentic AI系统主要是应用而非基础，因此其成功取决于终端用户和主要利益相关者的验证。主要用户验证其应用所需的工具和技术，与评估基础模型所使用的工具和技术截然不同。具有讽刺意味的是，在具备良好验证措施的情况下，许多场景中的基础模型可以由更简单、更快速且更具可解释性的处理核心逻辑的模型所替代。对于Agentic AI而言，有效性才是你需要的。LLMs只是可能实现它的一种选项。
英文摘要：
While AI agents have long been discussed and studied in computer science, today's Agentic AI systems are something new. We consider other definitions of Agentic AI and propose a new realist definition. Agentic AI is a software delivery mechanism, comparable to software as a service (SaaS), which puts an application to work autonomously in a complex enterprise setting. Recent advances in large language models (LLMs) as foundation models have driven excitement in Agentic AI. We note, however, that Agentic AI systems are primarily applications, not foundations, and so their success depends on validation by end users and principal stakeholders. The tools and techniques needed by the principal users to validate their applications are quite different from the tools and techniques used to evaluate foundation models. Ironically, with good validation measures in place, in many cases the foundation models can be replaced with much simpler, faster, and more interpretable models that handle core logic. When it comes to Agentic AI, validity is what you need. LLMs are one option that might achieve it.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
