| 引用本文: | 董益宏,姜雪,钱家如,王天,张克驰,金芝,李戈.基于大语言模型智能体的代码生成综述.软件学报,2026,37(8):3089-3115 |
| |
|
| |
|
|
| 本文已被：浏览 4386次 下载 1973次 |
码上扫一扫！ |
|
|
| 基于大语言模型智能体的代码生成综述 |
|
董益宏1,2, 姜雪1,2, 钱家如1,2, 王天1,2, 张克驰1,2, 金芝1,2, 李戈1,2
|
|
1.高可信软件技术教育部重点实验室 (北京大学), 北京 100871;2.北京大学 计算机学院, 北京 100871
|
|
| 摘要: |
| 基于大语言模型的代码生成智能体正在深刻地变革软件开发范式. 相较于之前的代码生成技术, 代码生成智能体展现出3大核心特征: 首先是自主性, 智能体能独立执行从任务分解到编码、调试的完整工作流; 其次是任务范围的广泛性, 其能力从生成代码片段扩展至覆盖软件开发的全生命周期; 最后是工程实践性的增强, 研究重心从模型算法创新转向流程管理、系统可靠性与工具集成等工程挑战. 近年来, 这一技术方向发展迅猛, 展现出巨大的应用潜力, 相关研究呈爆发式增长. 为此, 对基于大语言模型的代码生成智能体领域进行系统性的综述. 追溯该技术自诞生以来的发展脉络, 全面梳理并从方法论的视角对其核心技术(涵盖单智能体与多智能体系统)进行归纳和分类. 此外, 还总结代码生成智能体在软件开发全周期中的各项应用, 整理主流的评估基准与指标, 并盘点代表性的工具. 最后, 通过分析关键挑战, 展望该领域未来的长期核心研究方向. |
| 关键词: 代码生成 软件开发 大语言模型 大语言模型智能体 多智能体系统 |
| DOI：10.13328/j.cnki.jos.007593 |
| 分类号:TP311 |
| 基金项目:国家自然科学基金 (62192733, 62192730, 62192731); 国家重点研发计划 (2023YFB4503801); 湖北省重大项目(JD2023BAA024); 北京市重大科技项目 (Z251100008425005) |
|
| Survey on Code Generation with LLM-based Agents |
|
DONG Yi-Hong1,2, JIANG Xue1,2, QIAN Jia-Ru1,2, WANG Tian1,2, ZHANG Ke-Chi1,2, JIN Zhi1,2, LI Ge1,2
|
|
1.Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing 100871, China;2.School of Computer Science, Peking University, Beijing 100871, China
|
| Abstract: |
| Code generation agents based on large language models (LLMs) are profoundly revolutionizing the software development paradigm. Compared with previous code generation techniques, code generation agents have the following three core features. The first feature is autonomy. The agents can independently execute the entire workflow from task decomposition to coding and debugging. The second is expanded task scope. The agents’ capabilities have extended from generating code snippets to encompassing the full software development life cycle (SDLC). The third is the enhancement of engineering practicality. The research focus has shifted from model algorithmic innovation toward engineering challenges such as process management, system reliability, and tool integration. In recent years, this technical domain has witnessed rapid development and demonstrated tremendous application potential, with explosive growth in related research. To this end, this study presents a systematic review of the field of LLM-based code generation agents. The technology’s developmental trajectory since its inception is traced, and its core techniques including both single-agent and multi-agent systems are sorted out and categorized. Furthermore, this study summarizes both various applications of code generation agents in the full SDLC and the mainstream evaluation benchmarks and metrics, and reviews representative tools. Finally, by analyzing the key challenges, the long-term core research directions in the future for this field are pointed out. |
| Key words: code generation software development large language model (LLM) LLM-based agent multi-agent system |
|
|
|
|
