少做多得：智能体计算与替代架构选择的第一性原理探索
原标题：Doing Less with More: A First-Principles Exploration of the Suitability of Agentic Computing over Alternative Architectural Choices
AI 摘要
南卡罗来纳大学人工智能研究所与印度AI研究组织发表论文，在1000个算术表达式基准上对比七种功能调用架构：原生函数调用、REST、SOAP、MCP微服务、Groq云API与五个本地Ollama大模型直接作答、以及本地LLM调用MCP工具的智能体系统。结果显示确定性方法准确率100%且延迟可忽略，直接LLM作答最高准确率92.9%但延迟超22000倍，最佳MCP智能体准确率99.9%但延迟近100万倍。作者据此提出架构决策框架（ADF），主张按任务类型选择架构而非一律采用LLM。
正文节选
Doing Less with More: A First-Principles Exploration of the Suitability of Agentic Computing over Alternative Architectural Choices Abstract There is growing interest in automating business activities with Agentic Artificial Intelligence (AI) due to latter’s seeming ease of use. Never has it been easier, or costlier, to do less with more. However, little is known about when agents are preferable to established alternatives such as local computation, Representational State Transfer (REST), the Si