大语言模型在情感编码领域的研究综述

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

大型语言模型（LLMs）的进步推动了从代码生成辅助到自主编码代理的范式转变，催生了一种称为“氛围编码”（Vibe Coding）的新型开发方法论，其中开发者通过观察结果而非逐行代码理解来验证AI生成的实现。尽管这一新兴范式具有变革潜力，但其有效性仍待深入探索，实证研究揭示了人机协作中意外的生产力损失和根本性挑战。为填补这一空白，本综述首次对基于大型语言模型的氛围编码进行了全面系统的回顾，为这一变革性开发方法奠定了理论基础和实践框架。通过对1000多篇研究论文的系统分析，我们考察了整个氛围编码生态系统，审视了包括编码用LLMs、基于LLM的编码代理、编码代理的开发环境以及反馈机制在内的关键基础设施组件。我们首先通过约束马尔可夫决策过程将氛围编码形式化为一门正式学科，捕捉了人类开发者、软件项目与编码代理之间的动态三元关系。基于这一理论基础，我们进一步将现有实践综合为五种不同的开发模型：无约束自动化、迭代对话协作、规划驱动、测试驱动和上下文增强模型，从而提供了该领域的首个全面分类体系。关键的是，我们的分析表明，成功的氛围编码不仅依赖于代理能力，更取决于系统的上下文工程、完善的开发环境以及人机协作的开发模型。

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.