从目标到方面,重新审视:面向智能体AI系统的NFR模式语言
From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems
AI总结:
本文提出面向智能体AI系统的NFR模式语言,通过目标驱动的方法系统发现和模块化交叉切面问题,提升系统可靠性。
摘要:
智能体AI系统表现出众多交叉切面问题--安全、可观测性、成本管理、故障容忍--这些在当前实现中缺乏良好的模块化,导致AI项目难以达到生产阶段的高失败率。在RE 2004中提出的目标到方面方法表明,可以通过识别从i*目标模型中非功能性软目标来系统性地发现方面。本文重新审视并扩展了该方法,以面向智能体AI领域。我们提出了12个可重用模式的模式语言,组织在四个NFR类别(安全、可靠性、可观测性、成本管理)中,每个模式将i*目标模型映射到具体的方面实现,使用Rust的AOP框架。四个模式处理传统AOP文献中缺失的智能体特定交叉切面问题:工具作用域沙箱、提示注入检测、令牌预算管理以及行动审计追踪。我们扩展了V图模型,以捕捉智能体任务如何同时贡献于功能目标和非功能性软目标。我们通过案例研究分析了一个开源自主智能体框架,展示了目标驱动的方面发现如何系统性地识别和模块化交叉切面问题。该模式语言通过早期识别交叉切面问题,为工程可靠的智能体AI系统提供了一种系统的方法。
英文摘要:
Agentic AI systems exhibit numerous crosscutting concerns -- security, observability, cost management, fault tolerance -- that are poorly modularized in current implementations, contributing to the high failure rate of AI projects in reaching production. The goals-to-aspects methodology proposed at RE 2004 demonstrated that aspects can be systematically discovered from i* goal models by identifying non-functional soft-goals that crosscut functional goals. This paper revisits and extends that methodology to the agentic AI domain. We present a pattern language of 12 reusable patterns organized across four NFR categories (security, reliability, observability, cost management), each mapping an i* goal model to a concrete aspect implementation using an AOP framework for Rust. Four patterns address agent-specific crosscutting concerns absent from traditional AOP literature: tool-scope sandboxing, prompt injection detection, token budget management, and action audit trails. We extend the V-graph model to capture how agent tasks simultaneously contribute to functional goals and non-functional soft-goals. We validate the pattern language through a case study analyzing an open-source autonomous agent framework, demonstrating how goal-driven aspect discovery systematically identifies and modularizes crosscutting concerns. The pattern language offers a principled approach for engineering reliable agentic AI systems through early identification of crosscutting concerns.
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。