Neural Code Intelligence Survey

This is the repository of our paper: A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond.

Please do not hesitate to contact us or launch pull requests if you find any related papers that are missing in our paper.

News 📰

• Update on 2025/01/26: Version 1.6 released with additional topics on code preference learning 📖
• Update on 2024/11/01: Version 1.4 released with extra paper collections 📖
• Update on 2024/06/23: Version 1.2 released 🚀
• Update on 2024/03/19: Version 1.0 released 🚀
• Update on 2024/01/19: Add multiple reading lists 📖
• Update on 2023/12/29: Add Development Timelines 📅
• Update on 2023/12/25: Add Reading Lists, Merry Christmas 🍎🎄

Introduction 📜

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

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

Introducing the resources provided by our survey paper, slides is also available at here.

Timeline

The Development of Code Intelligence

Recent Work on Code Intelligence (Welcome PR) 📗

• DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation 2025.6
• Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning 2025.6
• CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction 2025.2
• Competitive Programming with Large Reasoning Models 2025.2
• EpiCoder: Encompassing Diversity and Complexity in Code Generation 2025.1
• WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models 2024.12
• FullStack Bench: Evaluating LLMs as Full Stack Coders 2024.12
• CodeDPO: Aligning Code Models with Self Generated and Verified Source Code 2024.11

Paper Collections / Tutorials 📚

• Language Models for Code 🤖
• Evaluations and Benchmarks 📊
• Preference Optimization 🍎
• Code Repair 🔧
• Reasoning with Code Synthesis 🧠
• Data Science 🔢
• Corpus containing Code Data 📚
• Code-Based Solutions for NLP Tasks 📝
• Code Empowered Agents 🤖
• Reinforcement Learning with CodeLMs 🎮
• Code Intelligence assists AI4Science 🧪
• Software Development 🛠️
• Multilingual 🌍
• Multimodal Code Generation 🎨
• Awesome Slides, Talks and Blogs 🧑‍🏫

Citation 📖

🫶 If you are interested in our work or find this repository helpful, please consider using the following citation format when referencing our paper:

@article{sun2024survey,
  title={A survey of neural code intelligence: Paradigms, advances and beyond},
  author={Sun, Qiushi and Chen, Zhirui and Xu, Fangzhi and Cheng, Kanzhi and Ma, Chang and Yin, Zhangyue and Wang, Jianing and Han, Chengcheng and Zhu, Renyu and Yuan, Shuai and others},
  journal={arXiv preprint arXiv:2403.14734},
  year={2024}
}

Acknowledgements

This is an open collaborative research project among:

Repository Contributors

Star History 🌟