代码大模型 / AI 编程 - arXivDaily 专题

2402.00689 2025-09-30 cs.CR cs.AI 79%

Ocassionally Secure: A Comparative Analysis of Code Generation Assistants

Ran Elgedawy, Porter Dosch, John Sadik, Senjuti Dutta, Anuj Gautam, Konstantinos Georgiou, Farzin Gholamrezae, Fujiao Ji, Kyungchan Lim, Qian Liu, Scott Ruoti

机构 * OpenAI ； Google（谷歌）； DeepSeek

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

Comments 12 pages, 2 figures

2508.17608 2025-09-30 cs.LG 79%

ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning

Wentao Tan, Qiong Cao, Chao Xue, Yibing Zhan, Changxing Ding, Xiaodong He

机构 * South China University of Technology（华南理工大学）； JD Future Academy（京东未来学院）； Wuhan University（武汉大学）

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

2408.09078 2025-09-30 cs.SE 79%

An Exploratory Study on Fine-Tuning Large Language Models for Secure Code Generation

Junjie Li, Fazle Rabbi, Cheng Cheng, Aseem Sangalay, Yuan Tian, Jinqiu Yang

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

Comments 37 pages, 8 figures

2509.19918 2025-09-25 cs.SE 79%

Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation

Micheline Bénédicte Moumoula, Serge Lionel Nikiema, Albérick Euraste Djire, Abdoul Kader Kabore, Jacques Klein, Tegawendé F. Bissyande

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

2508.05473 2025-09-25 cs.MM cs.AI cs.SD eess.AS 79%

Embedding Alignment in Code Generation for Audio

Sam Kouteili, Hiren Madhu, George Typaldos, Mark Santolucito

机构 * Yale University（耶鲁大学）； Columbia University（哥伦比亚大学）

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

Comments Accepted to NeurIPS 2025 AI4Music Workshop

2503.20197 2025-09-24 cs.SE 79%

A Preliminary Study on the Robustness of Code Generation by Large Language Models

Zike Li, Mingwei Liu, Anji Li, Kaifeng He, Yanlin Wang, Xin Peng, Zibin Zheng

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

Comments 10 pages

2509.17589 2025-09-23 cs.AI 79%

Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models

Jun Ling, Yao Qi, Tao Huang, Shibo Zhou, Yanqin Huang, Jiang Yang, Ziqi Song, Ying Zhou, Yang Yang, Heng Tao Shen, Peng Wang

机构 * School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）； Research Center for Scientific Data Hub, Zhejiang Lab, Hangzhou, China（浙江实验室科学数据中心研究中心）； School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）

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

Comments NeurIPS 2025

2507.15877 2025-09-23 cs.AI 79%

Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning

Simon Ouellette

机构 * Simon Ouellette

专题命中代码生成：program synthesis(title,abstract)；分类 cs.AI

Comments this version fixes errors in AlphaEvolve total % calculation, Table 3 DSL description, and adds clarifications in response to review criticisms

2504.07343 2025-09-23 cs.SE 79%

Code Generation with Small Language Models: A Codeforces-Based Study

Débora Souza, Rohit Gheyi, Lucas Albuquerque, Gustavo Soares, Márcio Ribeiro

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

Comments Accepted at International Conference on Machine Learning and Applications (ICMLA 2025)

2509.14373 2025-09-19 cs.SE 79%

CodeLSI: Leveraging Foundation Models for Automated Code Generation with Low-Rank Optimization and Domain-Specific Instruction Tuning

Huy Le, Phong Nguyen, Hao Do, Tuan Nguyen, Thien Pham, Anh Nguyen-Duc, Tho Quan

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

2509.13758 2025-09-18 cs.SE 79%

A Study on Thinking Patterns of Large Reasoning Models in Code Generation

Kevin Halim, Sin G. Teo, Ruitao Feng, Zhenpeng Chen, Yang Gu, Chong Wang, Yang Liu

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

2509.09101 2025-09-12 cs.CL 79%

TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla

Nishat Raihan, Antonios Anastasopoulos, Marcos Zampieri

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

2509.07941 2025-09-10 cs.CR cs.AI 79%

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation

Kai Ye, Liangcai Su, Chenxiong Qian

机构 * The University of Hong Kong（香港大学）

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

Comments This paper has been accepted by the ACM Conference on Computer and Communications Security (CCS) 2025

2409.11041 2025-09-09 cs.CL cs.RO 79%

Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming

Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen

机构 * Computational Linguistics, Department of Linguistics, University of Potsdam, Germany（波恩大学语言学系计算语言学部门）； German Research Center for Artificial Intelligence (DFKI), Berlin, Germany（德国人工智能研究中心（DFKI））

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

Comments Accepted to ITL4HRI workshop at RO-MAN 2025 conference

2509.01313 2025-09-09 cs.SE 79%

Aligning Requirement for Large Language Model's Code Generation

Zhao Tian, Junjie Chen

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

Comments Accepted by ICSE 2026

2508.15750 2025-09-01 cs.PL 79%

Active Learning for Neurosymbolic Program Synthesis

Celeste Barnaby, Qiaochu Chen, Ramya Ramalingam, Osbert Bastani, Isil Dillig

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

2508.19532 2025-08-28 cs.CL 79%

Alignment with Fill-In-the-Middle for Enhancing Code Generation

Houxing Ren, Zimu Lu, Weikang Shi, Haotian Hou, Yunqiao Yang, Ke Wang, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li

机构 * CUHK MMLab（CUHK语音实验室）； SenseTime Research（商汤科技研究院）； CPII under InnoHK（创新香港下的CPII）； Shanghai AI Laboratory（上海人工智能实验室）； Beihang University（北航）

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

Comments Accepted to EMNLP 2025 (main conference)

2508.18675 2025-08-27 cs.SE 79%

Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision

Xu Lu, Weisong Sun, Yiran Zhang, Ming Hu, Cong Tian, Zhi Jin, Yang Liu

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

2508.18148 2025-08-26 cs.CR cs.AI 79%

Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation

Haijian Ma, Daizong Liu, Xiaowen Cai, Pan Zhou, Yulai Xie

机构 * Huazhong University of Science and Technology（华中科技大学）； Peking University（北京大学）

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

Comments 18pages,5 figures,emnlp

2505.23060 2025-08-26 cs.CL 79%

Self-Correcting Code Generation Using Small Language Models

Jeonghun Cho, Deokhyung Kang, Hyounghun Kim, Gary Geunbae Lee

机构 * Graduate School of Artificial Intelligence, POSTECH（人工智能研究生院，POSTECH）； Department of Computer Science and Engineering, POSTECH（计算机科学与工程系，POSTECH）

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

Comments Accepted at EMNLP 2025 (Findings, long paper)

2508.12910 2025-08-22 cs.CR cs.AI cs.AR 79%

SecFSM: Knowledge Graph-Guided Verilog Code Generation for Secure Finite State Machines in Systems-on-Chip

Ziteng Hu, Yingjie Xia, Xiyuan Chen, Li Kuang

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

2508.10118 2025-08-19 cs.LG cs.CV 79%

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

Ke Niu, Haiyang Yu, Zhuofan Chen, Mengyang Zhao, Teng Fu, Bin Li, Xiangyang Xue

机构 * Fudan University（复旦大学）； ByteDance Inc（字节跳动公司）

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

2405.11430 2025-08-19 cs.CL 79%

MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation

Jianbo Dai, Jianqiao Lu, Yunlong Feng, Guangtao Zeng, Rongju Ruan, Ming Cheng, Dong Huang, Haochen Tan, Zhijiang Guo

机构 * University of Edinburgh（爱丁堡大学）； The University of Hong Kong（香港大学）； Harbin Institute of Technology（哈尔滨工业大学）； Singapore University of Technology and Design（新加坡科技设计大学）； South China University of Technology（华南理工大学）； City University of Hong Kong（香港城市大学）； University of Cambridge（剑桥大学）

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

Comments 43 pages, dataset and code are available at https://github.com/SparksofAGI/MHPP, leaderboard can be found at https://sparksofagi.github.io/MHPP/

2504.21569 2025-08-18 cs.SE 79%

A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models

Saima Afrin, Md Zahidul Haque, Antonio Mastropaolo

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

2503.11509 2025-08-15 cs.CL cs.CV 79%

TikZero: Zero-Shot Text-Guided Graphics Program Synthesis

Jonas Belouadi, Eddy Ilg, Margret Keuper, Hideki Tanaka, Masao Utiyama, Raj Dabre, Steffen Eger, Simone Paolo Ponzetto

专题命中代码生成：program synthesis(title,abstract)；分类 cs.CL

Comments Accepted at ICCV 2025 (highlight); Project page: https://github.com/potamides/DeTikZify

2505.21425 2025-08-13 cs.SE 79%

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

Naizhu Jin, Zhong Li, Tian Zhang, Qingkai Zeng

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

Comments Accepted by SEKE 2025

2508.07434 2025-08-12 cs.CL 79%

Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

Zhiyi Lyu, Jianguo Huang, Yanchen Deng, Steven Hoi, Bo An

机构 * Nanyang Technological University（南洋理工大学）； Alibaba Group（阿里巴巴集团）

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

2508.06414 2025-08-11 cs.SE 79%

What Builds Effective In-Context Examples for Code Generation?

Dongze Li, Songqiang Chen, Jialun Cao, Shing-Chi Cheung

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

2508.03622 2025-08-06 cs.AI 79%

Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework

Jialin Li, Jinzhe Li, Gengxu Li, Yi Chang, Yuan Wu

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

2508.03558 2025-08-06 cs.PL 79%

SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation

M Zafir Sadik Khan, Nowfel Mashnoor, Mohammad Akyash, Kimia Azar, Hadi Kamali

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

Comments Accepted to the IEEE International Conference on Computer Design (ICCD 2025)

1. 代码生成 4106 篇

Ocassionally Secure: A Comparative Analysis of Code Generation Assistants

ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning

An Exploratory Study on Fine-Tuning Large Language Models for Secure Code Generation

Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation

Embedding Alignment in Code Generation for Audio

A Preliminary Study on the Robustness of Code Generation by Large Language Models

Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models

Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning

Code Generation with Small Language Models: A Codeforces-Based Study

CodeLSI: Leveraging Foundation Models for Automated Code Generation with Low-Rank Optimization and Domain-Specific Instruction Tuning

A Study on Thinking Patterns of Large Reasoning Models in Code Generation

TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation

Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming

Aligning Requirement for Large Language Model's Code Generation

Active Learning for Neurosymbolic Program Synthesis

Alignment with Fill-In-the-Middle for Enhancing Code Generation

Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision

Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation

Self-Correcting Code Generation Using Small Language Models

SecFSM: Knowledge Graph-Guided Verilog Code Generation for Secure Finite State Machines in Systems-on-Chip

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation

A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models

TikZero: Zero-Shot Text-Guided Graphics Program Synthesis

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

What Builds Effective In-Context Examples for Code Generation?

Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework

SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation