arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.14734cs.SEcs.AIcs.CLcs.PL
收藏

神经代码智能综述:范式、进展与未来

A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond

Shanghai AI Laboratory(上海人工智能实验室);NetEase Fuxi AI Lab(网易伏羲人工智能实验室);Google DeepMind(谷歌DeepMind);School of Computer Science and Engineering at Nanyang Technological University(南洋理工大学计算机科学与工程学院)
Qiushi Sun, Zhirui Chen, Fangzhi Xu, Kanzhi Cheng, Chang Ma, Zhangyue Yin, Jianing Wang, Chengcheng Han, Renyu Zhu, Shuai Yuan, Qipeng Guo, Xipeng Qiu, Pengchen… 展开作者

Qiushi Sun, Zhirui Chen, Fangzhi Xu, Kanzhi Cheng, Chang Ma, Zhangyue Yin, Jianing Wang, Chengcheng Han, Renyu Zhu, Shuai Yuan, Qipeng Guo, Xipeng Qiu, Pengcheng Yin, Xiaoli Li, Fei Yuan, Lingpeng Kong, Xiang Li, Zhiyong Wu

AI总结:

本综述系统回顾了神经代码智能领域的范式演变与技术进展,涵盖50余个模型及680余项研究,揭示了其在跨领域应用中的潜力与未来研究方向。

摘要:

神经代码智能——利用深度学习来理解、生成和优化代码——对整个社会具有巨大的变革潜力影响。该领域连接了自然语言与编程语言,在过去几年中引起了两个研究社区研究人员的极大关注。本综述对代码智能的进展进行了系统和按时间顺序的回顾,涵盖超过50个代表性模型及其变体、超过20个类别的任务,以及对超过680篇相关工作的广泛覆盖。我们遵循历史发展进程,追溯了不同研究阶段的范式转变(例如,从使用循环神经网络对代码进行建模到大语言模型时代)。同时,我们重点介绍了贯穿不同阶段的模型、任务和评估方面的重大技术转变。对于应用,我们也观察到了一个共同演变的转变。它跨越了从最初致力于处理特定场景,到在其快速扩张期间探索各种不同的任务,再到目前专注于应对日益复杂和多样的现实世界挑战。基于我们对发展轨迹的考察,我们进一步研究了代码智能与更广泛的机器智能之间新兴的协同作用,揭示了新的跨领域机遇,并说明了代码智能在各个领域的巨大影响。最后,我们深入探讨了与该领域相关的机遇和挑战,并阐明了我们对最有前途的研究方向的见解。与本综述相关的一个持续动态更新的项目和资源已在https://github.com/QiushiSun/Awesome-Code-Intelligence发布。

英文摘要:

Neural Code Intelligence -- leveraging deep learning to understand, generate, and optimize code -- holds immense potential for transformative impacts on the whole society. Bridging the gap between Natural Language and Programming Language, this domain has drawn significant attention from researchers in both research communities over the past few years. This survey presents a systematic and chronological review of the advancements in code intelligence, encompassing over 50 representative models and their variants, more than 20 categories of tasks, and an extensive coverage of over 680 related works. We follow the historical progression to trace the paradigm shifts across different research phases (e.g., from modeling code with recurrent neural networks to the era of Large Language Models). Concurrently, we highlight the major technical transitions in models, tasks, and evaluations spanning through different stages. For applications, we also observe a co-evolving shift. It spans from initial endeavors to tackling specific scenarios, through exploring a diverse array of tasks during its rapid expansion, to currently focusing on tackling increasingly complex and varied real-world challenges. Building on our examination of the developmental trajectories, we further investigate the emerging synergies between code intelligence and broader machine intelligence, uncovering new cross-domain opportunities and illustrating the substantial influence of code intelligence across various domains. Finally, we delve into both the opportunities and challenges associated with this field, alongside elucidating our insights on the most promising research directions. An ongoing, dynamically updated project and resources associated with this survey have been released at https://github.com/QiushiSun/Awesome-Code-Intelligence.

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。

↑