代码大模型 / AI 编程 - arXivDaily 专题

2506.19794 2025-11-14 cs.CL cs.AI cs.IR cs.LG cs.MA 67%

Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study

Yuqi Zhu, Yi Zhong, Jintian Zhang, Ziheng Zhang, Shuofei Qiao, Yujie Luo, Lun Du, Da Zheng, Ningyu Zhang, Huajun Chen

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

Comments AAAI 2026 (oral)

2502.16395 2025-11-10 cs.LG cs.AI cs.CL cs.HC 67%

AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science

Qiuhai Zeng, Claire Jin, Xinyue Wang, Yuhan Zheng, Qunhua Li

机构 * Pennsylvania State University（宾夕法尼亚州立大学）； Carnegie Mellon University（卡内基梅隆大学）； International Monetary Fund（国际货币基金组织）

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

Comments Accepted to 2025 EMNLP findings

2505.18574 2025-11-07 cs.PL cs.AI cs.AR cs.LG 67%

Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators

Charles Hong, Sahil Bhatia, Alvin Cheung, Yakun Sophia Shao

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

Comments 10 pages + appendices

2511.02869 2025-11-06 cs.SE cs.AI cs.PL 67%

Analysis of AdvFusion: Adapter-based Multilingual Learning for Code Large Language Models

Amirreza Esmaeili, Fahd Seddik, Yongyi Ji, Fatemeh Fard, Fuxiang Chen

机构 * University of British Columbia（不列颠哥伦比亚大学）； University of Leicester（利兹大学）

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

2511.01884 2025-11-06 cs.LG cs.AI cs.CL cs.DC 67%

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

Zijian Zhang, Rong Wang, Shiyang Li, Yuebo Luo, Mingyi Hong, Caiwen Ding

机构 * University of Minnesota, Twin Cities（明尼苏达大学，双城分校）

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

2511.01758 2025-11-04 cs.LG cs.AI cs.CL 67%

RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks

Mian Wu, Gavin Zhang, Sewon Min, Sergey Levine, Aviral Kumar

机构 * Shanghai Jiao Tong University（上海交通大学）； UC Berkeley（加州大学伯克利分校）； Carnegie Mellon University（卡内基梅隆大学）

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

Comments Project page: https://mianwu01.github.io/RLAC_website/

2503.02854 2025-11-03 cs.CL cs.AI cs.LG 67%

(How) Do Language Models Track State?

Belinda Z. Li, Zifan Carl Guo, Jacob Andreas

机构 * MIT EECS（麻省理工学院电子工程与计算机科学系）

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

Comments 21 pages, 17 figures, 1 table. Code: http://github.com/belindal/state-tracking

2510.08396 2025-10-24 cs.LG cs.AI cs.CL 67%

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts

Heming Zou, Yunliang Zang, Wutong Xu, Yao Zhu, Xiangyang Ji

机构 * Department of Automation, Tsinghua University（自动化系，清华大学）； Academy of Medical Engineering and Translational Medicine, Tianjin University（医学工程与转化医学学院，天津大学）

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

Comments NeurIPS 2025 accepted paper

2311.02433 2025-10-15 cs.SE cs.AI cs.FL cs.LG cs.LO 67%

Can ChatGPT support software verification?

Christian Janßen, Cedric Richter, Heike Wehrheim

机构 * Carl-von-Ossietzky Universität Oldenburg（奥尔登堡卡尔·冯·奥西特齐大学）

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

Comments accepted at Fundamental Approaches to Software Engineering 2024

2503.02783 2025-10-10 cs.CL cs.AI cs.LG 67%

Teaching Your Models to Understand Code via Focal Preference Alignment

Jie Wu, Haoling Li, Xin Zhang, Xiao Liu, Yangyu Huang, Jianwen Luo, Yizhen Zhang, Zuchao Li, Ruihang Chu, Yujiu Yang, Scarlett Li

机构 * Tsinghua University（清华大学）； Microsoft Research（微软研究院）； CASIA（中国科学院自动化研究所）； Wuhan University（武汉大学）

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

Comments Accepted by EMNLP'25

2506.10974 2025-10-09 cs.CL cs.AI cs.HC cs.LG cs.MA 67%

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

Yixin Ou, Yujie Luo, Jingsheng Zheng, Lanning Wei, Zhuoyun Yu, Shuofei Qiao, Jintian Zhang, Da Zheng, Yuren Mao, Yunjun Gao, Huajun Chen, Ningyu Zhang

机构 * Zhejiang University（浙江大学）； Ant Group（蚂蚁集团）； Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph（浙江大学-蚂蚁集团知识图谱联合实验室）

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

Comments Ongoing work

2506.15655 2025-10-06 cs.SE cs.AI cs.CL cs.IR 67%

cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree

Yilin Zhang, Xinran Zhao, Zora Zhiruo Wang, Chenyang Yang, Jiayi Wei, Tongshuang Wu

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

2509.25420 2025-10-01 cs.AI cs.CL cs.LG 67%

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search

Yingqian Cui, Zhenwei Dai, Pengfei He, Bing He, Hui Liu, Xianfeng Tang, Jingying Zeng, Suhang Wang, Yue Xing, Jiliang Tang, Benoit Dumoulin

机构 * Michigan State University（密歇根州立大学）； Amazon（亚马逊）； Pennsylvania State University（宾夕法尼亚州立大学）

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

2507.14688 2025-10-01 cs.CL cs.AI cs.LG 67%

Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations

Mohammed Alkhowaiter, Norah Alshahrani, Saied Alshahrani, Reem I. Masoud, Alaa Alzahrani, Deema Alnuhait, Emad A. Alghamdi, Khalid Almubarak

机构 * Refine AI ； ASAS AI ； University of Bisha（比沙大学）； University College London（伦敦大学学院）； King Salman Global Academy for Arabic（萨勒曼全球阿拉伯学院）； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； King Abdulaziz University（阿卜杜勒阿齐兹大学）； HUMAIN

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

2507.05418 2025-09-29 cs.CL cs.AI cs.LG 67%

Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning

Jaedong Hwang, Kumar Tanmay, Seok-Jin Lee, Ayush Agrawal, Hamid Palangi, Kumar Ayush, Ila Fiete, Paul Pu Liang

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

2509.20837 2025-09-26 cs.SE cs.AI cs.CL 67%

Verification Limits Code LLM Training

Srishti Gureja, Elena Tommasone, Jingyi He, Sara Hooker, Matthias Gallé, Marzieh Fadaee

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

2509.16241 2025-09-23 cs.CL cs.AI cs.PL 67%

REAMS: Reasoning Enhanced Algorithm for Maths Solving

Eishkaran Singh, Tanav Singh Bajaj, Siddharth Nayak

机构 * Thapar（塔帕尔学院）； University of British Columbia（不列颠哥伦比亚大学）； Massachusetts Institute of Technology（麻省理工学院）

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

2412.06947 2025-09-22 cs.AR cs.AI cs.LG cs.PL 67%

PyraNet: A Multi-Layered Hierarchical Dataset for Verilog

Bardia Nadimi, Ghali Omar Boutaib, Hao Zheng

机构 * Dept. of Computer Science \& Eng. University of South Florida Tampa, Florida, United States

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

2410.11900 2025-09-22 cs.AI cs.CL cs.LG cs.LO 67%

FLARE: Faithful Logic-Aided Reasoning and Exploration

Erik Arakelyan, Pasquale Minervini, Pat Verga, Patrick Lewis, Isabelle Augenstein

机构 * University of Copenhagen（哥本哈根大学）； University of Edinburgh（爱丁堡大学）； Cohere ； NVIDIA

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

Comments Published at EMNLP 2025

2508.00033 2025-09-17 cs.SE cs.AI cs.CL 67%

GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries

Nuno Fachada, Daniel Fernandes, Carlos M. Fernandes, Bruno D. Ferreira-Saraiva, João P. Matos-Carvalho

机构 * Copelabs, Lusófona University（Copelabs与卢斯奥法纳大学）； Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI)（技术与系统中心（UNINOVA-CTS）及智能系统关联实验室）； CICANT, Lusófona University（CICANT与卢斯奥法纳大学）

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

Comments The peer-reviewed version of this paper is published in Future Internet at https://doi.org/10.3390/fi17090412. This version is typeset by the author and differs only in pagination and typographical detail

Journal ref Future Internet. 2025; 17(9):412

2402.15729 2025-09-10 cs.AI cs.CL cs.PL 67%

How Do Humans Write Code? Large Models Do It the Same Way Too

Long Li, Xuzheng He, Haozhe Wang, Linlin Wang, Liang He

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

2509.03537 2025-09-05 cs.CL cs.AI cs.LG 67%

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models

Cheng-Kai Yeh, Hsing-Wang Lee, Chung-Hung Kuo, Hen-Hsen Huang

机构 * Department of Mathematical Sciences National Chengchi University Taipei Taiwan（数学科学系国立政治大学台北台湾）； Department of Computer Science National Chengchi University Taipei Taiwan（计算机科学系国立政治大学台北台湾）； Institute of Information Science Academia Sinica Taipei Taiwan（信息科学研究所中国学术院台北台湾）； National Chengchi University（国立政治大学）

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

Comments 7 pages, accepted by CIKM 2025 as a short paper

2508.12790 2025-08-19 cs.AI cs.CL cs.LG 67%

Reinforcement Learning with Rubric Anchors

Zenan Huang, Yihong Zhuang, Guoshan Lu, Zeyu Qin, Haokai Xu, Tianyu Zhao, Ru Peng, Jiaqi Hu, Zhanming Shen, Xiaomeng Hu, Xijun Gu, Peiyi Tu, Jiaxin Liu, Wenyu Chen, Yuzhuo Fu, Zhiting Fan, Yanmei Gu, Yuanyuan Wang, Zhengkai Yang, Jianguo Li, Junbo Zhao

机构 * Inclusion AI ； Ant Group（蚂蚁集团）； Zhejiang University（浙江大学）

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

Comments technical report

2508.08641 2025-08-13 cs.LG cs.AI cs.CL 67%

MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time

Peter Phan, Dhruv Agarwal, Kavitha Srinivas, Horst Samulowitz, Pavan Kapanipathi, Andrew McCallum

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

2508.03936 2025-08-07 cs.CR cs.CL cs.LG cs.SE 67%

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Xiangzhe Xu, Guangyu Shen, Zian Su, Siyuan Cheng, Hanxi Guo, Lu Yan, Xuan Chen, Jiasheng Jiang, Xiaolong Jin, Chengpeng Wang, Zhuo Zhang, Xiangyu Zhang

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

Comments The first two authors (Xiangzhe Xu and Guangyu Shen) contributed equally to this work

2508.02823 2025-08-06 cs.HC cs.AI cs.CL cs.SE 67%

NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification

Wenshuo Zhang, Leixian Shen, Shuchang Xu, Jindu Wang, Jian Zhao, Huamin Qu, Linping Yuan

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； University of Waterloo（滑铁卢大学）

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

Comments Accepted in UIST 2025

2508.00952 2025-08-05 cs.CY cs.AI cs.PL cs.SE 67%

Academic Vibe Coding: Opportunities for Accelerating Research in an Era of Resource Constraint

Matthew G Crowson, Leo Celi A. Celi

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

2504.07448 2025-08-05 cs.LG cs.AI cs.CL 67%

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

Juzheng Zhang, Jiacheng You, Ashwinee Panda, Tom Goldstein

机构 * University of Maryland（马里兰大学）； Tsinghua University（清华大学）

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

Comments COLM 2025

2412.15441 2025-08-01 cs.SE cs.AI cs.LG 67%

Insights into resource utilization of code small language models serving with runtime engines and execution providers

Francisco Durán, Matias Martinez, Patricia Lago, Silverio Martínez-Fernández

机构 * Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）

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

Comments Accepted in Journal of Systems and Software (JSS). For its published version refer to the Journal of JSS

2503.05200 2025-07-24 cs.CL cs.AI cs.LG cs.NI 67%

ORANSight-2.0: Foundational LLMs for O-RAN

Pranshav Gajjar, Vijay K. Shah

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

1. 代码生成 4092 篇

Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study

AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science

Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators

Analysis of AdvFusion: Adapter-based Multilingual Learning for Code Large Language Models

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks

(How) Do Language Models Track State?

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts

Can ChatGPT support software verification?

Teaching Your Models to Understand Code via Focal Preference Alignment

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search

Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations

Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning

Verification Limits Code LLM Training

REAMS: Reasoning Enhanced Algorithm for Maths Solving

PyraNet: A Multi-Layered Hierarchical Dataset for Verilog

FLARE: Faithful Logic-Aided Reasoning and Exploration

GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries

How Do Humans Write Code? Large Models Do It the Same Way Too

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models

Reinforcement Learning with Rubric Anchors

MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification

Academic Vibe Coding: Opportunities for Accelerating Research in an Era of Resource Constraint

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

Insights into resource utilization of code small language models serving with runtime engines and execution providers

ORANSight-2.0: Foundational LLMs for O-RAN