代码大模型 / AI 编程 - arXivDaily 专题

2511.00087 2025-11-04 cs.SE cs.AI 62%

Adding New Capability in Existing Scientific Application with LLM Assistance

Anshu Dubey, Akash Dhruv

机构 * Argonne National Laboratory（阿贡国家实验室）

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

Comments 8 pages, 4 figures, submitted to The 1st International Workshop on Foundational large Language Models Advances for HPC in Asia

2505.18901 2025-11-04 cs.LG cs.AI 62%

PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models

Xiaoyan Hu, Lauren Pick, Ho-fung Leung, Farzan Farnia

机构 * Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）

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

Comments 39 pages

2505.14970 2025-10-31 cs.AI cs.LG 62%

Self-Evolving Curriculum for LLM Reasoning

Xiaoyin Chen, Jiarui Lu, Minsu Kim, Dinghuai Zhang, Jian Tang, Alexandre Piché, Nicolas Gontier, Yoshua Bengio, Ehsan Kamalloo

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

2510.25378 2025-10-30 cs.CL cs.AI 62%

Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy

Junichiro Niimi

机构 * Meijo University（名古屋大学）； RIKEN AIP（理化学研究所AIP）

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

2510.23674 2025-10-29 cs.SE cs.AI cs.CR 62%

RefleXGen:The unexamined code is not worth using

Bin Wang, Hui Li, AoFan Liu, BoTao Yang, Ao Yang, YiLu Zhong, Weixiang Huang, Yanping Zhang, Runhuai Huang, Weimin Zeng

机构 * 1 School of Electronic ； Computer Engineering,Peking University 2 Apability \& Platform Business Dept., China Mobile Internet Co. 3 China Telecom Cloud Technology Co., Ltd.

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

Journal ref ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5

2504.20434 2025-10-28 cs.SE cs.AI 62%

ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

Manish Bhattarai, Miguel Cordova, Minh Vu, Javier Santos, Ismael Boureima, Dan O'Malley

机构 * Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

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

2510.23208 2025-10-28 cs.LG cs.AI 62%

Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks

Amal Abed, Ivan Lukic, Jörg K. H. Franke, Frank Hutter

机构 * University of Freiburg（弗赖堡大学）； ELLIS Institute Tübingen（图宾根ELLIS研究所）； Open-Sci Collective（开放科学集体）； LAION ； Prior Labs（Prior实验室）

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

Comments Presented at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: The 4th Deep Learning for Code Workshop (DL4C)

2508.20119 2025-10-28 cs.SE cs.LG 62%

LLM Agents for Generating Microservice-based Applications: how complex is your specification?

Daniel M. Yellin

机构 * post.runi.ac.il（runi学院）

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

Comments 24 pages + 5 pages appendices. 7 Figures. 10 Tables

2504.16485 2025-10-28 cs.SE cs.AI 62%

On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices

Syed Mohammad Kashif, Peng Liang, Amjed Tahir

机构 * School of Computer Science, Wuhan University（武汉大学计算机科学学院）； School of Mathematical and Computational Sciences, Massey University（马斯赛大学数学与计算科学学院）

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

Comments Preprint accepted for publication in ACM Transactions on Software Engineering and Methodology (TOSEM), 2025

2510.21407 2025-10-27 cs.NE cs.AI cs.SE 62%

REvolution: An Evolutionary Framework for RTL Generation driven by Large Language Models

Kyungjun Min, Kyumin Cho, Junhwan Jang, Seokhyeong Kang

机构 * Department of Electrical Engineering, Pohang University of Science and Technology（电子工程系，釜山科学技术大学）

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

Comments Accepted for publication at the 2026 Asia and South Pacific Design Automation Conference (ASP-DAC)

2303.16459 2025-10-27 cs.AR cs.AI cs.LG 62%

GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization

Stefan Abi-Karam, Cong Hao

机构 * School of Electrical and Computer Engineering, Georgia Institute of Technology（电气与计算机工程学院，佐治亚理工学院）； Georgia Tech Research Institute（佐治亚理工研究机构）

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

Comments 10 pages, 7 figures, 4 tables, 3 listings

2507.16068 2025-10-24 cs.RO cs.AI cs.LG cs.MA 62%

Compositional Coordination for Multi-Robot Teams with Large Language Models

Zhehui Huang, Guangyao Shi, Yuwei Wu, Vijay Kumar, Gaurav S. Sukhatme

机构 * Department of Computer Science, University of Southern California（计算机科学系，南加州大学）； GRASP Lab, University of Pennsylvania（GRASP实验室，宾夕法尼亚大学）

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

Comments IEEE International Symposium on Multi-Robot & Multi-Agent Systems (MRS 2025) Oral

2510.19895 2025-10-24 cs.CL cs.AI 62%

Large Language Model enabled Mathematical Modeling

Guoyun Zhang

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

2505.14827 2025-10-24 cs.CL cs.AI 62%

Text Generation Beyond Discrete Token Sampling

Yufan Zhuang, Liyuan Liu, Chandan Singh, Jingbo Shang, Jianfeng Gao

机构 * UC San Diego（加州大学圣地亚哥分校）； Microsoft Research（微软研究院）

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

2510.18897 2025-10-23 cs.DC cs.AI cs.DB cs.SE 62%

AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators

Jacopo Tagliabue

机构 * Jacopo Tagliabue（独立研究者）

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

Comments Pre-print IAAA workshop submission

2504.03931 2025-10-23 cs.CL cs.AI 62%

NAACL2025 Tutorial: Adaptation of Large Language Models

Zixuan Ke, Yifei Ming, Shafiq Joty

机构 * Salesforce AI Research（Salesforce人工智能研究）

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

Comments NAACL2025 Tutorial

2506.11442 2025-10-22 cs.SE cs.LG 62%

ReVeal: Self-Evolving Code Agents via Reliable Self-Verification

Yiyang Jin, Kunzhao Xu, Hang Li, Xueting Han, Yanmin Zhou, Cheng Li, Jing Bai

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

2510.17705 2025-10-21 cs.AI cs.CL 62%

Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models

Dayan Pan, Zhaoyang Fu, Jingyuan Wang, Xiao Han, Yue Zhu, Xiangyu Zhao

机构 * SCSE, Beihang University（北京航空航天大学系统工程学院）； ERC of ACAT, MOE（教育部人工智能教育联合体）； City University of Hong Kong（香港城市大学）； Huawei Technologies Ltd.（华为技术有限公司）； Key Lab of DIM, MIIT（信息通信技术重点实验室）； SEM, Beihang University（北京航空航天大学电子机械学院）； Zhejiang University of Technology（浙江工业大学）

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

Comments Accepted by CIKM' 25

2510.16533 2025-10-21 cs.AI cs.LG 62%

Hey Pentti, We Did It Again!: Differentiable vector-symbolic types that prove polynomial termination

Eilene Tomkins-Flanagan, Connor Hanley, Mary A. Kelly

机构 * Department of Cognitive Science, Carleton University（认知科学系，卡尔顿大学）

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

Journal ref Tomkins Flanagan, E., Hanley, C., & Kelly, M. A. (2025, July). Paper presented at MathPsych / ICCM 2025. Via mathpsych.org/presentation/1997

2510.16470 2025-10-21 cs.DB cs.AI cs.SE 62%

Declarative Techniques for NL Queries over Heterogeneous Data

Elham Khabiri, Jeffrey O. Kephart, Fenno F. Heath, Srideepika Jayaraman, Fateh A. Tipu, Yingjie Li, Dhruv Shah, Achille Fokoue, Anu Bhamidipaty

机构 * IBM Research（IBM研究院）

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

2510.16022 2025-10-21 cs.LG cs.SE 62%

Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization

Changsheng Wang, Xin Chen, Sijia Liu, Ke Ding

机构 * The OPTML Lab, Michigan State University（密歇根州立大学OPTML实验室）； Intel（英特尔）； IBM Research（IBM研究）

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

2506.12713 2025-10-21 cs.SE cs.CL 62%

Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?

Xiangyang Li, Xiaopeng Li, Kuicai Dong, Quanhu Zhang, Rongju Ruan, Xinyi Dai, Xiaoshuang Liu, Shengchun Xu, Yasheng Wang, Ruiming Tang

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室）

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

Comments EMNLP 2025 Findings

2407.06153 2025-10-20 cs.SE cs.CL 62%

What's Wrong with Your Code Generated by Large Language Models? An Extensive Study

Shihan Dou, Haoxiang Jia, Shenxi Wu, Huiyuan Zheng, Muling Wu, Yunbo Tao, Ming Zhang, Mingxu Chai, Jessica Fan, Zhiheng Xi, Rui Zheng, Yueming Wu, Ming Wen, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang

机构 * Fudan University（复旦大学）； Peking University（北京大学）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）； Shanghai Qiji Zhifeng Co., Ltd.（上海启智风科技有限公司）； Huazhong University of Science and Technology（华中科技大学）

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

Comments Accepted by SCIENCE CHINA Information Sciences (SCIS)

2510.10661 2025-10-15 cs.CL cs.AI 62%

AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generation

Omid Reza Heidari, Siobhan Reid, Yassine Yaakoubi

机构 * Concordia University（康科德大学）

专题命中代码生成：coding agent(abstract)；分类 cs.CL、cs.AI

Comments Accepted at NeurIPS 2025, ER "Efficient Reasoning" workshop

2510.11536 2025-10-14 cs.SE cs.AI 62%

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs

Manaal Basha, Aimeê M. Ribeiro, Jeena Javahar, Cleidson R. B. de Souza, Gema Rodríguez-Pérez

机构 * University of British Columbia（不列颠哥伦比亚大学）； Federal University of Pará（帕拉联邦大学）

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

Comments ICSME 2025 Tool Demonstration Track

2510.11498 2025-10-14 cs.LG cs.CL 62%

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

Yuhang Li, Chenchen Zhang, Ruilin Lv, Ao Liu, Ken Deng, Yuanxing Zhang, Jiaheng Liu, Wiggin Zhou, Bo Zhou

机构 * LLM Department, Tencent（腾讯大语言模型部门）； Peking University（北京大学）； Nanjing University（南京大学）

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

2510.08623 2025-10-13 cs.CL cs.LG 62%

PARSE: LLM Driven Schema Optimization for Reliable Entity Extraction

Anubhav Shrimal, Aryan Jain, Soumyajit Chowdhury, Promod Yenigalla

机构 * RBS Tech Sciences, Amazon（RBS科技科学，亚马逊）

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

Comments EMNLP 2025 Industry Track

2510.08612 2025-10-13 cs.SE cs.AI 62%

Impact of LLMs on Team Collaboration in Software Development

Devang Dhanuka

机构 * MS Data Science Program（数据科学项目）； Rochester Institute of Technology（罗切斯特理工学院）

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

2412.05393 2025-10-10 cs.LG cs.AI cs.AR 62%

HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design

Jinwei Tang, Jiayin Qin, Kiran Thorat, Chen Zhu-Tian, Yu Cao, Yang, Zhao, Caiwen Ding

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

2510.05529 2025-10-08 cs.CL cs.LG 62%

H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference

Harshil Vejendla

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

Comments MIT URTC 2025 Technical Paper (Oral), 5 pages, 1 figure

1. 代码生成 4127 篇

Adding New Capability in Existing Scientific Application with LLM Assistance

PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models

Self-Evolving Curriculum for LLM Reasoning

Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy

RefleXGen:The unexamined code is not worth using

ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks

LLM Agents for Generating Microservice-based Applications: how complex is your specification?

On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices

REvolution: An Evolutionary Framework for RTL Generation driven by Large Language Models

GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization

Compositional Coordination for Multi-Robot Teams with Large Language Models

Large Language Model enabled Mathematical Modeling

Text Generation Beyond Discrete Token Sampling

AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators

NAACL2025 Tutorial: Adaptation of Large Language Models

ReVeal: Self-Evolving Code Agents via Reliable Self-Verification

Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models

Hey Pentti, We Did It Again!: Differentiable vector-symbolic types that prove polynomial termination

Declarative Techniques for NL Queries over Heterogeneous Data

Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization

Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?

What's Wrong with Your Code Generated by Large Language Models? An Extensive Study

AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generation

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

PARSE: LLM Driven Schema Optimization for Reliable Entity Extraction

Impact of LLMs on Team Collaboration in Software Development

HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design

H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference