代码大模型 / AI 编程 - arXivDaily 专题

2510.19116 2025-10-23 cs.CL cs.AI cs.LG 82%

That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation

Jaesung Bae, Cameron Churchwell, Mitchell Hermon, Tsun-An Hsieh, Jocelyn Xu, Yekaterina Yegorova, Mark Hasegawa-Johnson, Heng Ji

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

2403.00046 2025-10-22 cs.SE cs.AI cs.CL 82%

Exploring Data-Efficient Adaptation of Large Language Models for Code Generation

Xue Jiang, Yihong Dong, Zhiyuan Fan, Zhi Jin, Wenpin Jiao, Ge Li

机构 * Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education（高可信软件技术重点实验室（北京大学））； School of Computer Science, Peking University, Beijing（计算机学院（北京大学））

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

Comments Accepted by TOSEM

2510.17598 2025-10-21 cs.AI cs.CL cs.LG 82%

Reasoning Distillation and Structural Alignment for Improved Code Generation

Amir Jalilifard, Anderson de Rezende Rocha, Marcos Medeiros Raimundo

机构 * Universidade Estadual de Campinas（坎皮纳斯州立大学）

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

2510.10739 2025-10-14 cs.LG cs.AI cs.SE 82%

A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications

Shivani Shukla, Himanshu Joshi

机构 * University of San Francisco（旧金山大学）； Vector Institute for Artificial Intelligence（人工智能向量研究所）

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

Comments Peer-reviewed and accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) DynaFront 2025 Workshop (https://sites.google.com/view/dynafrontneurips25)

2510.02387 2025-10-13 cs.SE cs.AI cs.LG 82%

CWM: An Open-Weights LLM for Research on Code Generation with World Models

FAIR CodeGen team, Jade Copet, Quentin Carbonneaux, Gal Cohen, Jonas Gehring, Jacob Kahn, Jannik Kossen, Felix Kreuk, Emily McMilin, Michel Meyer, Yuxiang Wei, David Zhang, Kunhao Zheng, Jordi Armengol-Estapé, Pedram Bashiri, Maximilian Beck, Pierre Chambon, Abhishek Charnalia, Chris Cummins, Juliette Decugis, Zacharias V. Fisches, François Fleuret, Fabian Gloeckle, Alex Gu, Michael Hassid, Daniel Haziza, Badr Youbi Idrissi, Christian Keller, Rahul Kindi, Hugh Leather, Gallil Maimon, Aram Markosyan, Francisco Massa, Pierre-Emmanuel Mazaré, Vegard Mella, Naila Murray, Keyur Muzumdar, Peter O'Hearn, Matteo Pagliardini, Dmitrii Pedchenko, Tal Remez, Volker Seeker, Marco Selvi, Oren Sultan, Sida Wang, Luca Wehrstedt, Ori Yoran, Lingming Zhang, Taco Cohen, Yossi Adi, Gabriel Synnaeve

机构 * Meta ； FAIR CodeGen Team（FAIR CodeGen团队）

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

Comments 58 pages

2510.08610 2025-10-13 cs.SE cs.AI cs.LG 82%

Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model

Imranur Rahman, Md Rayhanur Rahman

机构 * North Carolina State University（北卡罗来纳州立大学）； The University of Alabama（阿拉巴马大学）

专题命中代码生成：repository(title,abstract)；分类 cs.SE、cs.AI、cs.LG

Comments Accepted to Context Collection Workshop co-located with ASE 2025

2506.03930 2025-09-30 cs.SE cs.AI cs.CL 82%

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation

Yuansheng Ni, Ping Nie, Kai Zou, Xiang Yue, Wenhu Chen

机构 * University of Waterloo（滑铁卢大学）； Carnegie Mellon University（卡内基梅隆大学）

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

2506.20008 2025-09-01 cs.AI cs.PL cs.SE 82%

QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges

Abdul Basit, Minghao Shao, Muhammad Haider Asif, Nouhaila Innan, Muhammad Kashif, Alberto Marchisio, Muhammad Shafique

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

Comments To appear at the IEEE International Conference on Quantum Artificial Intelligence (QAI), Naples, Italy, November 2025

2508.15866 2025-08-25 cs.PL cs.LG cs.SE 82%

Correctness-Guaranteed Code Generation via Constrained Decoding

Lingxiao Li, Salar Rahili, Yiwei Zhao

机构 * Netflix

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

Comments Published at COLM 2025

2508.09012 2025-08-13 cs.CL cs.AI cs.LG 82%

LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA

Adrián Gude, Roi Santos-Ríos, Francisco Prado-Valiño, Ana Ezquerro, Jesús Vilares

机构 * Universidade da Coruña（科鲁纳大学）； CITIC Departamento de Ciencias de la Computación y Tecnologías de la Información（CITIC计算机科学与信息技术部门）

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

Comments Accepted to SemEval 2025. Camera-ready version

2508.03678 2025-08-06 cs.CL cs.LG cs.PL 82%

More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation

Yangtian Zi, Harshitha Menon, Arjun Guha

机构 * Northeastern University（东北大学）； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）

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

2507.12367 2025-07-23 cs.SE cs.AI cs.PL 82%

GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities

Diganta Misra, Nizar Islah, Victor May, Brice Rauby, Zihan Wang, Justine Gehring, Antonio Orvieto, Muawiz Chaudhary, Eilif B. Muller, Irina Rish, Samira Ebrahimi Kahou, Massimo Caccia

机构 * ELLIS Institute Tübingen（图宾根ELLIS研究所）； MPI-IS Tübingen（图宾根MPI研究所）； Mila Quebec AI Institute（魁北克AI研究所）； Google（谷歌）； Polytechnique Montréal（蒙特利尔高等理工学院）； McGill University（麦吉尔大学）； Moderne（Moderne公司）； Gologic（Gologic公司）； Tübingen AI Center（图宾根人工智能中心）； Université de Montréal（蒙特利尔大学）； ServiceNow Research（ServiceNow研究）

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

Comments Version 2 of the dataset from: arXiv:2411.05830

2507.08719 2025-07-14 cs.CL cs.AI cs.SE 82%

Multilingual Multimodal Software Developer for Code Generation

Linzheng Chai, Jian Yang, Shukai Liu, Wei Zhang, Liran Wang, Ke Jin, Tao Sun, Congnan Liu, Chenchen Zhang, Hualei Zhu, Jiaheng Liu, Xianjie Wu, Ge Zhang, Tianyu Liu, Zhoujun Li

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

Comments Preprint

2412.20545 2025-07-09 cs.SE cs.CL cs.HC cs.LG 82%

The Impact of Prompt Programming on Function-Level Code Generation

Ranim Khojah, Francisco Gomes de Oliveira Neto, Mazen Mohamad, Philipp Leitner

机构 * Chalmers University of Technology and University of Gothenburg（查尔姆斯理工大学和哥德堡大学）； RISE Research Institutes of Sweden（瑞典RISE研究机构）

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

Comments Accepted at Transactions on Software Engineering (TSE). CodePromptEval dataset and replication package on GitHub: https://github.com/icetlab/CodePromptEval

2506.22776 2025-07-01 cs.SE cs.AI cs.PL 82%

Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation

Sen Fang, Weiyuan Ding, Antonio Mastropaolo, Bowen Xu

机构 * NC State University（北卡罗来纳州立大学）； William & Mary（威廉与玛丽学院）

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

Comments 13 pages, 6 figures

2506.20926 2025-07-01 cs.CR 82%

Towards Generalized and Stealthy Watermarking for Generative Code Models

Haoxuan Li, Jiale Zhang, Xiaobing Sun, Xiapu Luo

专题命中代码生成：code model(title,abstract)；code generation(abstract)

Comments 13 pages

2502.20380 2025-06-30 cs.LG cs.AI cs.CL 82%

Multi-Turn Code Generation Through Single-Step Rewards

Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Wayne Chen, Alexander M Rush, Wenting Zhao, Sanjiban Choudhury

机构 * Mila- Quebec AI Institute（魁北克AI研究所）； Cornell University（康奈尔大学）

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

Comments 9 pages (not including references or appendix); 5 figures (in main paper); (v2) camera-ready version

2407.21049 2025-06-26 cs.CL cs.AI cs.LG 82%

Evaluating Long Range Dependency Handling in Code Generation LLMs

Yannick Assogba, Donghao Ren

机构 * Apple（苹果公司）

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

Comments 36 pages, 18 figures

Journal ref Transactions on Machine Learning Research, 2025. ISSN 2835-8856. https://openreview.net/forum?id=yzACI2vFaX

2506.07313 2025-06-10 cs.CR 82%

SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows

Rebecca Saul, Hao Wang, Koushik Sen, David Wagner

专题命中代码生成：code generation(title,abstract)；coding agent(abstract)

2501.13978 2025-05-30 cs.CL cs.AI cs.SE 82%

Chain of Grounded Objectives: Bridging Process and Goal-oriented Prompting for Code Generation

Sangyeop Yeo, Seung-won Hwang, Yu-Seung Ma

机构 * Electronics and Telecommunications Research Institute（电子电信研究院）； Department of Computer Science and Engineering, Seoul National University（计算机科学与工程系，首尔国立大学）

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

Comments Accepted by ECOOP 2025 main conference

2502.11466 2025-05-22 cs.LG cs.CL cs.SE 82%

GiFT: Gibbs Fine-Tuning for Code Generation

Haochen Li, Wanjin Feng, Xin Zhou, Zhiqi Shen

机构 * Nanyang Technological University（南洋理工大学）

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

Comments Accepted to ACL 2025

2505.12900 2025-05-20 cs.SE cs.AI cs.CG cs.CL cs.DB 82%

AutoGEEval: A Multimodal and Automated Framework for Geospatial Code Generation on GEE with Large Language Models

Shuyang Hou, Zhangxiao Shen, Huayi Wu, Jianyuan Liang, Haoyue Jiao, Yaxian Qing, Xiaopu Zhang, Xu Li, Zhipeng Gui, Xuefeng Guan, Longgang Xiang

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

2504.05500 2025-04-11 cs.AI cs.LG cs.SE 82%

Prism: Dynamic and Flexible Benchmarking of LLMs Code Generation with Monte Carlo Tree Search

Vahid Majdinasab, Amin Nikanjam, Foutse Khomh

机构 * Huawei（华为）； Polytechnique Montreal（蒙特利尔理工学院）

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

2503.08738 2025-03-21 cs.SE cs.LG cs.PL 82%

Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model

Janis Zenkner, Tobias Sesterhenn, Christian Bartelt

机构 * TU Clausthal（克劳斯塔尔工业大学）

专题命中代码生成：program synthesis(title,abstract)；分类 cs.SE、cs.LG、cs.PL

Comments Accepted at ICLR 2025 Workshop Deep Learning for Code

2412.18573 2025-03-18 cs.SE cs.AI cs.CL 82%

Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark

Dewu Zheng, Yanlin Wang, Ensheng Shi, Xilin Liu, Yuchi Ma, Hongyu Zhang, Zibin Zheng

机构 * Sun Yat-sen University（中山大学）； Huawei Cloud Computing Technologies Co., Ltd（华为云计算技术有限公司）； Chongqing University（重庆大学）

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

2502.19852 2025-02-28 cs.SE cs.AI cs.CL 82%

ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments

Hojae Han, Seung-won Hwang, Rajhans Samdani, Yuxiong He

机构 * Snowflake AI Research（Snowflake AI研究院）； Seoul National University（首尔大学）

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

Comments ICLR 2025

2502.18726 2025-02-27 cs.SE cs.AI cs.LG 82%

Deep-Bench: Deep Learning Benchmark Dataset for Code Generation

Alireza Daghighfarsoodeh, Chung-Yu Wang, Hamed Taherkhani, Melika Sepidband, Mohammad Abdollahi, Hadi Hemmati, Hung Viet Pham

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

2407.07064 2025-02-27 cs.SE cs.AI cs.CR cs.LG 82%

Prompting Techniques for Secure Code Generation: A Systematic Investigation

Catherine Tony, Nicolás E. Díaz Ferreyra, Markus Mutas, Salem Dhiff, Riccardo Scandariato

机构 * Hamburg University of Technology（汉堡工业大学）

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

Comments Work partially supported by the EU-funded project Sec4AI4Sec: Cybersecurity for AI-Augmented Systems (grant no. 101120393) - ACCEPTED at ACM Transactions on Software Engineering and Methodology (Feb. 2025)

2408.02487 2025-02-26 cs.SE cs.AI cs.LG 82%

LiCoEval: Evaluating LLMs on License Compliance in Code Generation

Weiwei Xu, Kai Gao, Hao He, Minghui Zhou

机构 * School of Computer Science, Peking University（北京大学计算机学院）； University of Science and Technology Beijing（北京科技大学）； Carnegie Mellon University（卡内基梅隆大学）

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

Comments The 47th International Conference on Software Engineering(ICSE 2025)

2502.11829 2025-02-18 cs.CL cs.AI cs.SE 82%

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities

Hanbin Wang, Xiaoxuan Zhou, Zhipeng Xu, Keyuan Cheng, Yuxin Zuo, Kai Tian, Jingwei Song, Junting Lu, Wenhui Hu, Xueyang Liu

机构 * Peking University（北京大学）； Northeastern University（东北大学）； University of Hong Kong（香港大学）

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

Comments 15 pages

1. 代码生成 4132 篇

That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation

Exploring Data-Efficient Adaptation of Large Language Models for Code Generation

Reasoning Distillation and Structural Alignment for Improved Code Generation

A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications

CWM: An Open-Weights LLM for Research on Code Generation with World Models

Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation

QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges

Correctness-Guaranteed Code Generation via Constrained Decoding

LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA

More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation

GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities

Multilingual Multimodal Software Developer for Code Generation

The Impact of Prompt Programming on Function-Level Code Generation

Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation

Towards Generalized and Stealthy Watermarking for Generative Code Models

Multi-Turn Code Generation Through Single-Step Rewards

Evaluating Long Range Dependency Handling in Code Generation LLMs

SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows

Chain of Grounded Objectives: Bridging Process and Goal-oriented Prompting for Code Generation

GiFT: Gibbs Fine-Tuning for Code Generation

AutoGEEval: A Multimodal and Automated Framework for Geospatial Code Generation on GEE with Large Language Models

Prism: Dynamic and Flexible Benchmarking of LLMs Code Generation with Monte Carlo Tree Search

Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model

Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark

ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments

Deep-Bench: Deep Learning Benchmark Dataset for Code Generation

Prompting Techniques for Secure Code Generation: A Systematic Investigation

LiCoEval: Evaluating LLMs on License Compliance in Code Generation

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities