大语言模型下的氛围编码研究综述

A Survey of Vibe Coding with Large Language Models

October 14, 2025

作者: Yuyao Ge, Lingrui Mei, Zenghao Duan, Tianhao Li, Yujia Zheng, Yiwei Wang, Lexin Wang, Jiayu Yao, Tianyu Liu, Yujun Cai, Baolong Bi, Fangda Guo, Jiafeng Guo, Shenghua Liu, Xueqi Cheng

cs.AI

摘要

大型語言模型（LLMs）的進步催生了一種從代碼生成輔助到自主編碼代理的範式轉變，促成了一種名為「氛圍編碼」（Vibe Coding）的新開發方法論，其中開發者通過觀察結果而非逐行代碼理解來驗證AI生成的實現。儘管其具有變革潛力，這一新興範式的有效性仍未被充分探索，實證研究揭示了人機協作中意外的生產力損失和根本性挑戰。為填補這一空白，本調查首次對基於大型語言模型的氛圍編碼進行了全面而系統的審視，為這一變革性開發方法建立了理論基礎和實踐框架。通過對超過1000篇研究論文的系統分析，我們考察了整個氛圍編碼生態系統，審視了包括編碼用LLMs、基於LLM的編碼代理、編碼代理的開發環境以及反饋機制在內的關鍵基礎設施組件。我們首先通過一個約束馬爾可夫決策過程（Constrained Markov Decision Process）將氛圍編碼形式化，從而將其作為一門正式學科引入，該過程捕捉了人類開發者、軟件項目和編碼代理之間的動態三元關係。基於這一理論基礎，我們隨後將現有實踐綜合為五種不同的開發模型：無約束自動化、迭代對話協作、規劃驅動、測試驅動和上下文增強模型，從而提供了該領域的首個全面分類法。關鍵的是，我們的分析揭示，成功的氛圍編碼不僅依賴於代理能力，還依賴於系統化的上下文工程、完善的開發環境以及人機協作開發模型。

English

The advancement of large language models (LLMs) has catalyzed a paradigm shift from code generation assistance to autonomous coding agents, enabling a novel development methodology termed "Vibe Coding" where developers validate AI-generated implementations through outcome observation rather than line-by-line code comprehension. Despite its transformative potential, the effectiveness of this emergent paradigm remains under-explored, with empirical evidence revealing unexpected productivity losses and fundamental challenges in human-AI collaboration. To address this gap, this survey provides the first comprehensive and systematic review of Vibe Coding with large language models, establishing both theoretical foundations and practical frameworks for this transformative development approach. Drawing from systematic analysis of over 1000 research papers, we survey the entire vibe coding ecosystem, examining critical infrastructure components including LLMs for coding, LLM-based coding agent, development environment of coding agent, and feedback mechanisms. We first introduce Vibe Coding as a formal discipline by formalizing it through a Constrained Markov Decision Process that captures the dynamic triadic relationship among human developers, software projects, and coding agents. Building upon this theoretical foundation, we then synthesize existing practices into five distinct development models: Unconstrained Automation, Iterative Conversational Collaboration, Planning-Driven, Test-Driven, and Context-Enhanced Models, thus providing the first comprehensive taxonomy in this domain. Critically, our analysis reveals that successful Vibe Coding depends not merely on agent capabilities but on systematic context engineering, well-established development environments, and human-agent collaborative development models.