arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.18538cs.SEcs.CL
收藏

从代码基础模型到代理与应用:全面综述与代码智能的实用指南

From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence

Jian Yang, Xianglong Liu, Weifeng Lv, Ken Deng, Shawn Guo, Lin Jing, Yizhi Li, Shark Liu, Xianzhen Luo, Yuyu Luo, Changzai Pan, Ensheng Shi, Yingshui Tan, Rensh… 展开作者

Jian Yang, Xianglong Liu, Weifeng Lv, Ken Deng, Shawn Guo, Lin Jing, Yizhi Li, Shark Liu, Xianzhen Luo, Yuyu Luo, Changzai Pan, Ensheng Shi, Yingshui Tan, Renshuai Tao, Jiajun Wu, Xianjie Wu, Zhenhe Wu, Daoguang Zan, Chenchen Zhang, Wei Zhang, He Zhu, Terry Yue Zhuo, Kerui Cao, Xianfu Cheng, Jun Dong, Shengjie Fang, Zhiwei Fei, Xiangyuan Guan, Qipeng Guo, Zhiguang Han, Joseph James, Tianqi Luo, Renyuan Li, Yuhang Li, Yiming Liang, Congnan Liu, Jiaheng Liu, Qian Liu, Ruitong Liu, Tyler Loakman, Xiangxin Meng, Chuang Peng, Tianhao Peng, Jiajun Shi, Mingjie Tang, Boyang Wang, Haowen Wang, Yunli Wang, Fanglin Xu, Zihan Xu, Fei Yuan, Ge Zhang, Jiayi Zhang, Xinhao Zhang, Wangchunshu Zhou, Hualei Zhu, King Zhu, Bryan Dai, Aishan Liu, Zhoujun Li, Chenghua Lin, Tianyu Liu, Chao Peng, Kai Shen, Libo Qin, Shuangyong Song, Zizheng Zhan, Jiajun Zhang, Jie Zhang, Zhaoxiang Zhang, Bo Zheng

AI总结:

本文综述了代码基础模型到代理的应用,分析了代码LLM的完整生命周期,并通过实验探讨了其性能优化与实际应用中的挑战。

摘要:

大型语言模型(LLMs)通过使自然语言描述能够直接转换为功能性代码,从根本上改变了自动化软件开发,通过诸如GitHub Copilot(微软)、Cursor(Anysphere)、Trae(字节跳动)和Claude Code(Anthropic)等工具推动了商业应用。尽管该领域已从基于规则的系统发展到基于Transformer的架构,其在HumanEval等基准测试中的性能从单个数字提升到超过95%的成功率。在本文中,我们提供了一个全面的综合和实用指南(一系列分析和探测实验),系统地考察了代码LLMs的完整模型生命周期,从数据整理到训练后通过先进的提示范式、代码预训练、监督微调、强化学习和自主编码代理。我们分析了通用LLMs(GPT-4、Claude、LLaMA)和代码专用LLMs(StarCoder、Code LLaMA、DeepSeek-Coder和QwenCoder)的代码能力,并批判性地审视了技术、设计决策和权衡。进一步,我们阐述了学术研究(例如基准测试和任务)与实际应用(例如与软件相关代码任务)之间的研究-实践差距,包括代码正确性、安全性、大型代码库的上下文意识以及与开发工作流的整合,并将有前途的研究方向映射到实际需求。最后,我们进行了一系列实验,对代码预训练、监督微调和强化学习进行了全面分析,涵盖了扩展定律、框架选择、超参数敏感性、模型架构和数据集比较。

英文摘要:

Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot (Microsoft), Cursor (Anysphere), Trae (ByteDance), and Claude Code (Anthropic). While the field has evolved dramatically from rule-based systems to Transformer-based architectures, achieving performance improvements from single-digit to over 95\% success rates on benchmarks like HumanEval. In this work, we provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs, systematically examining the complete model life cycle from data curation to post-training through advanced prompting paradigms, code pre-training, supervised fine-tuning, reinforcement learning, and autonomous coding agents. We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder), critically examining the techniques, design decisions, and trade-offs. Further, we articulate the research-practice gap between academic research (e.g., benchmarks and tasks) and real-world deployment (e.g., software-related code tasks), including code correctness, security, contextual awareness of large codebases, and integration with development workflows, and map promising research directions to practical needs. Last, we conduct a series of experiments to provide a comprehensive analysis of code pre-training, supervised fine-tuning, and reinforcement learning, covering scaling law, framework selection, hyperparameter sensitivity, model architectures, and dataset comparisons.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑