一句话：提出 Vibe Engineering 框架，以意图工程与实现工程两大支柱，把一次性提示式的 vibe coding 升级为可重复的多智能体 AI 辅助软件创建流程。
“Vibe coding”让非技术用户（software maker）通过描述期望结果来构建应用，只关注最终产物而不关心底层代码，Lovable、Bubble、Glide 等平台的爆发式增长使“AIware：人人可做软件”的愿景成真。然而，这一进展目前局限于复杂度有限的应用，并伴随严重的不可靠与失败风险，其根源在于一次性提示难以支撑完整的需求理解与工程化实现。本文以 90 分钟技术简报的形式提出 Vibe Engineering：一个超越单次提示的结构化框架，通过定义角色、规定制品、编排可重复流程来组织 AI 辅助软件开发。框架由两大支柱构成：(1) 意图工程，借助多智能体对话、心理理论（ToM）原则与测试驱动的需求精化，深入理解用户真实需求；(2) 实现工程，在专门的智能体执行环境（AEE）中由多智能体团队依据已被验证的意图自主构建、测试与验证软件。简报还剖析该领域的技术挑战，并指出具体的软件工程研究机会。
“Vibe coding” represents a paradigm shift where non-technical users, or “software makers”, create applications by describing the desired outcome, focusing entirely on the final output rather than the underlying code. This movement, propelled by hyper-growth platforms like Lovable, Bubble, and Glide, actualizes the vision of “AIware”: software for all, by all. However, this remarkable progress is currently confined to applications of limited complexity and introduces significant risks of unreliability and failure. This 90-minute technical briefing introduces Vibe Engineering, a structured framework for AI-assisted software creation that goes beyond one-shot prompts. The framework operates by defining roles, specifying artifacts, and orchestrating a repeatable process. It is built on two foundational pillars: (1) Intent Engineering, which focuses on deeply understanding user needs through multi-agent dialogues, Theory of Mind (ToM) principles, and test-driven requirement refinement; and (2) Realization Engineering, a specialized Agent Execution Environment (AEE) where multi-agent teams autonomously build, test, and verify the software based on the user’s validated intent. This briefing provides an insider’s view of the technical challenges in this domain and surfaces concrete software engineering research opportunities.
@inproceedings{paperbot11740,
title = {Vibe Engineering},
author = {Keheliya Gallaba and Zhiyu Fan and Jiahuei (Justina) Lin and Filipe R. Cogo and Benjamin Rombaut and Dayi Lin and Ahmed E. Hassan},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3774748.3776599}
}