面向智能体软件工程的规范驱动开发：利用人机协作
Spec-Driven Development for Agentic Software Engineering: Harnessing Human-Agent Teamwork
- Universidad Politécnica de Madrid（马德里理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对智能体软件工程的生产率悖论，本文提出规范驱动开发（SDD），构建相关模型、管控机制及人机交互模式，为团队级智能体软件工程提供支撑规范。
AI中文摘要：
背景：软件工程正从 vibe coding 这类 AI 辅助实践（助手加速个体开发者）转向智能体软件工程（Agentic Software Engineering, ASE），该领域中自主智能体被委派目标级任务。但行业报告显示存在生产率悖论：个体生产率提升的同时，团队吞吐量、评审能力和稳定性却因忽视团队级软件工程规范而下降。目标：本文旨在建立规范驱动开发（Spec-Driven Development, SDD）的概念与方法论基础，作为团队级 ASE 的支撑规范，并刻画管控机制（即团队管控智能体行为的技术与方法论机制）。方法：我们主要基于灰色文献开展概念分析，包括 ASE 愿景与路线图论文、从业者报告、演讲及工具，因为目前尚未建立同行评审证据及统一的产学研词汇。结果：以范式演进的比较刻画为概念框架，本文呈现：（i）SDD 的社会技术模型，其中规范作为人与智能体之间的契约载体；（ii）管控机制的操作刻画，区分智能体周围的技术管控与团队周围的方法论管控，并附实例；（iii）五种人机交互模式的类型学，以此重新定义人类角色。结论：我们得出结论，SDD 以规范为中心的形式重构了 vibe coding 所消解的契约：问责性、可验证性和可转移性。鉴于证据基础尚不成熟，本工作旨在作为达成产学研共识的第一步而非已验证的理论，并概述未来实证验证的研究议程。
英文摘要：
Context: Software engineering is moving from AI-assisted practices like vibe coding, in which assistants accelerate individual developers, towards Agentic Software Engineering (ASE), in which autonomous agents are delegated goal-level tasks. However, industry reports a productivity paradox: as individual productivity increases, team throughput, review capacity, and stability degrade because team-scale software engineering discipline is neglected. Objective: This paper aims to establish the conceptual and methodological foundations of Spec-Driven Development (SDD) as an enabling discipline for ASE at team scale and characterize the harness, i.e., the technical and methodological mechanisms through which teams govern agent behavior. Method: We conducted a conceptual analysis drawing predominantly on gray literature, including ASE vision and roadmap papers, practitioner reports, talks, and tooling, because peer-reviewed evidence and a shared academic-industrial vocabulary are not yet established. Results: Using a comparative characterization of the paradigm progression as conceptual framing, the article presents (i) a socio-technical model of SDD in which specifications act as the contract substrate between humans and agents; (ii) an operational characterization of the harness, distinguishing the technical harness around the agent from the methodological harness around the team, with worked examples; and (iii) a typology of five human--agent interaction patterns through which the human role is redefined. Conclusion: We conclude that SDD reconstitutes, in specification-centric form, the contracts that vibe coding dissolves: accountability, verifiability, and transferability. Given the immaturity of the evidence base, this work is presented as a first step toward academic-industrial consensus rather than a validated theory, and outlines a research agenda for future empirical validation.
