代码大模型 / AI 编程

FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models

Xihang Yue, Linchao Zhu, Yi Yang

专题命中 代码生成 ：code generation(abstract)；repository(abstract)；分类 cs.CL

Large Language Models for Code Summarization

Balázs Szalontai, Gergő Szalay, Tamás Márton, Anna Sike, Balázs Pintér, Tibor Gregorics

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.AI、cs.LG

Comments technical report with 11 pages, 1 figure, 10 tables

Perplexed: Understanding When Large Language Models are Confused

Nathan Cooper, Torsten Scholak

专题命中 代码生成 ：code generation(abstract)；code model(abstract)；分类 cs.SE

Investigating the Efficacy of Large Language Models for Code Clone Detection

Mohamad Khajezade, Jie JW Wu, Fatemeh Hendijani Fard, Gema Rodríguez-Pérez, Mohamed Sami Shehata

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.CL、cs.AI

LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems

Mohamad Fakih, Rahul Dharmaji, Yasamin Moghaddas, Gustavo Quiros Araya, Oluwatosin Ogundare, Mohammad Abdullah Al Faruque

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.CL、cs.AI

Comments 12 pages; 8 figures; Appearing in the 46th International Conference on Software Engineering: Software Engineering in Practice; for demo website, see https://sites.google.com/uci.edu/llm4plc/home

Enhancing Code Intelligence Tasks with ChatGPT

Kang Yang, Xinjun Mao, Shangwen Wang, Tanghaoran Zhang, Bo Lin, Yanlin Wang, Yihao Qin, Zhang Zhang, Xiaoguang Mao

专题命中 代码生成 ：code generation(abstract)；code model(abstract)；分类 cs.SE

Comments 10 pages, 5 figures

When Do Program-of-Thoughts Work for Reasoning?

Zhen Bi, Ningyu Zhang, Yinuo Jiang, Shumin Deng, Guozhou Zheng, Huajun Chen

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.CL、cs.AI

Comments AAAI 2024

ANPL: Towards Natural Programming with Interactive Decomposition

Di Huang, Ziyuan Nan, Xing Hu, Pengwei Jin, Shaohui Peng, Yuanbo Wen, Rui Zhang, Zidong Du, Qi Guo, Yewen Pu, Yunji Chen

专题命中 代码生成 ：program synthesis(abstract)；分类 cs.CL、cs.AI、cs.LG

The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation

Dung Nguyen Manh, Nam Le Hai, Anh T. V. Dau, Anh Minh Nguyen, Khanh Nghiem, Jin Guo, Nghi D. Q. Bui

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.CL、cs.AI

Comments Accepted at EMNLP 2023, Long Findings

Beryllium: Neural Search for Algorithm Implementations

Adithya Kulkarni, Mohna Chakraborty, Yonas Sium, Sai Charishma Valluri, Wei Le, Qi Li

专题命中 代码生成 ：repository(abstract)；program synthesis(abstract)；分类 cs.SE

PAC Prediction Sets for Large Language Models of Code

Adam Khakhar, Stephen Mell, Osbert Bastani

专题命中 代码生成 ：code generation(abstract)；code model(abstract)；分类 cs.LG

Comments Proceedings of the 40th International Conference on Machine Learning

Journal ref PMLR 202, 2023

Code Execution with Pre-trained Language Models

Chenxiao Liu, Shuai Lu, Weizhu Chen, Daxin Jiang, Alexey Svyatkovskiy, Shengyu Fu, Neel Sundaresan, Nan Duan

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.CL、cs.AI

Comments Accepted to the Findings of ACL 2023

GPT-based Open-Ended Knowledge Tracing

Naiming Liu, Zichao Wang, Richard G. Baraniuk, Andrew Lan

专题命中 代码生成 ：code generation(abstract)；program synthesis(abstract)；分类 cs.LG

Comments This paper is accepted at EMNLP 2022. The code can be found at https://github.com/lucy66666/OKT

Assisted Specification of Code Using Search

Steven P. Reiss

专题命中 代码生成 ：code generation(abstract)；program synthesis(abstract)；分类 cs.SE

How Readable is Model-generated Code? Examining Readability and Visual Inspection of GitHub Copilot

Naser Al Madi

专题命中 代码生成 ：code generation(abstract)；program synthesis(abstract)；分类 cs.SE

NatGen: Generative pre-training by "Naturalizing" source code

Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar Devanbu, Baishakhi Ray

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.AI、cs.LG

Comments Accepted to be published in ESEC/FSE 2022

AutoTSG: Learning and Synthesis for Incident Troubleshooting

Manish Shetty, Chetan Bansal, Sai Pramod Upadhyayula, Arjun Radhakrishna, Anurag Gupta

专题命中 代码生成 ：program synthesis(abstract)；分类 cs.SE、cs.AI、cs.LG

A Study of Single Statement Bugs Involving Dynamic Language Features

Li Sui, Shawn Rasheed, Amjed Tahir, Jens Dietrich

专题命中 代码生成 ：code generation(abstract)；program repair(abstract)；分类 cs.SE

Comments Accepted at the 30th IEEE/ACM International Conference on Program Comprehension (ICPC 2022) - ERA track

Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations

Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang

专题命中 代码生成 ：code model(abstract)；分类 cs.SE、cs.AI、cs.LG

Comments Accepted at SIGIR 2021

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

David Bieber, Charles Sutton, Hugo Larochelle, Daniel Tarlow

专题命中 代码生成 ：program repair(abstract)；program synthesis(abstract)；分类 cs.LG

Comments Accepted at NeurIPS 2020

On Repair with Probabilistic Attribute Grammars

Manos Koukoutos, Mukund Raghothaman, Etienne Kneuss, Viktor Kuncak

专题命中 代码生成 ：program repair(abstract)；program synthesis(abstract)；分类 cs.PL

Automatic Generation of Python Programs Using Context-Free Grammars

Kamel Yamani, Marwa Naïr, Riyadh Baghdadi

专题命中 代码生成 ：code generation(abstract,comments)；分类 cs.CL、cs.LG、cs.PL

Comments This work was presented at the 2nd Languages, Architectures, and Tools for Heterogeneous Computing (LATHC) Workshop 2024, organized in conjunction with the IEEE/ACM International Symposium on Code Generation and Optimization (CGO)

AskIt: Unified Programming Interface for Programming with Large Language Models

Katsumi Okuda, Saman Amarasinghe

专题命中 代码生成 ：code generation(abstract,comments)；分类 cs.SE、cs.AI、cs.PL

Comments To be published in 2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)

Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglement

逃离低维重叠：通过高维稀疏解缠的多任务模型合并

Yihang Zhang, Shengke Sun, Junjie Wen, Feng Zeng

机构 * Central South University（中南大学） ； Nanjing University of Science and Technology（南京理工大学） ； Hefei University of Technology（合肥工业大学） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 针对多任务模型合并的任务干扰问题，本文提出基于SAEs的高维稀疏解缠合并框架，结合GR-ZOO实现选择性合并，在Qwen2.5系列模型的多任务上优于现有基线。

Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification

功能熵：通过不确定性量化预测LLM生成代码的功能正确性

Dylan Bouchard, Mohit Singh Chauhan, Zeya Ahmad, Ho-Kyeong Ra

机构 * CVS Health（CVS健康） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 针对LLM生成代码功能不正确的问题，提出基于功能等价性的不确定性量化方法（功能熵），在多个编程语言和模型上优于现有方法。

Comments Accepted at EMNLP 2026 (Main)

When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study

当监督式不确定性量化集成能提升大语言模型幻觉检测性能？一项鲁棒性研究

Mohit Singh Chauhan, Vipin Gyanchandani, Dylan Bouchard

机构 * CVS Health（CVS健康公司） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 本文研究监督式UQ集成对LLM幻觉检测的鲁棒性，在多模型、多数据集、多生成范式下分析其性能，发现其多数场景优于单个评分器，采样黑盒集成效果接近全集成。

LLM Agents Perform Controlled Experiments Using Simulation Models

大语言模型智能体使用模拟模型开展对照实验

Yuchen Xia, Michael Weyrich, Nasser Jazdi, Johannes Stümpfle, Johannes Sigel, Akshay Narla, Gavin K. Reynolds, Anna Jawor-Baczynska, Pol Llopart

机构 * Institute for Industrial Automation and Software Engineering（工业自动化与软件工程研究所） ； University of Stuttgart（斯图加特大学） ； AstraZeneca（阿斯利康） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.CL、cs.AI

AI总结 本研究提出多智能体框架，将LLM与高保真模拟模型结合，使LLM智能体可开展制药工艺设计的对照实验，生成更具体可操作的优化建议，在工业场景中表现更优。

Comments Accepted at the 31st IEEE International Conference on Emerging Technologies and Factory Automation ETFA 2026

Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems

低延迟系统中的工具制作与自我进化大语言模型智能体

Kalle Kujanpää, Ning Liu, Shahnawaz Alam, Yeshwanth Reddy Sura, Tianyu Yang, Kristina Klinkner, Shervin Malmasi

机构 * Amazon（亚马逊） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.SE、cs.CL、cs.LG

AI总结 研究如何解决生产LLM智能体因重复生成代码浪费延迟和可靠性的问题，提出用智能工具制作管道取代推理时编码循环，部署该方法使系统更快、更可靠、易操作，降低延迟和错误率，提高可审计性。

Comments To appear at EMNLP 2026 Industry Track

Agentic Transaction: Towards ACID-Compliant Agent Systems

智能体事务：面向ACID兼容的智能体系统

Zhaoyan Sun, Xiaoxiao Wang, Guoliang Li

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 该研究提出ACID兼容的智能体事务框架，开发对应数据智能体，在基准测试中较含Claude Code的现有智能体提升10.6%，为构建可信可扩展AI智能体开辟新方向。

No Universal Signal Predicts Sample-Level LLM Regression under Version Updates

没有通用信号可预测版本更新下的样本级大语言模型退化

Jia Sheng, Yiwei Lu

机构 * University of Ottawa（渥太华大学） ； Vector Institute（向量研究所） 纠错

专题命中 代码生成 ：code generation(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 本文研究如何用推理时信号预测LLM版本更新导致的样本级退化，对比单模型与跨版本信号，发现信号有效性具任务依赖性且无通用最优信号，部分跨版本信号可支持选择性回退，从业者可据此选择信号。