代码大模型 / AI 编程

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache

Dinghong Song, Yuan Feng, Yiwei Wang, Shangye Chen, Cyril Guyot, Filip Blagojevic, Hyeran Jeon, Pengfei Su, Dong Li

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

Comments 10 pages, 6 figures

Edit Flows: Flow Matching with Edit Operations

Marton Havasi, Brian Karrer, Itai Gat, Ricky T. Q. Chen

机构 * FAIR at Meta（Meta 的 FAIR） 纠错

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

Vector Symbolic Algebras for the Abstraction and Reasoning Corpus

Isaac Joffe, Chris Eliasmith

机构 * Centre for Theoretical Neuroscience（理论神经科学中心） ； David R. Cheriton School of Computer Science（大卫·R·切里顿计算机科学学院） ； University of Waterloo（滑铁库大学） ； Department of Philosophy（哲学系） ； Department of Systems Design Engineering（系统设计工程系） 纠错

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

How Natural Language Proficiency Shapes GenAI Code for Software Engineering Tasks

Ruksit Rojpaisarnkit, Youmei Fan, Kenichi Matsumoto, Raula Gaikovina Kula

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

Comments 7 pages, 4 tables, 1 figure

PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI

Athma Narayanan, Mahesh Subedar, Omesh Tickoo

机构 * Intel Corporation USA（英特尔公司） 纠错

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

Comments Appeared in the Design Automation Conference (DAC) 2025, Workshop Poster on June 22, 2025

VFocus: Better Verilog Generation from Large Language Model via Focused Reasoning

Zhuorui Zhao, Bing Li, Grace Li Zhang, Ulf Schlichtmann

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

Comments accepted by SOCC 2025

ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Search

Vincenzo Collura, Karim Tit, Laura Bussi, Eleonora Giunchiglia, Maxime Cordy

机构 * University of Luxembourg（卢森堡大学） ； Imperial College London（伦敦帝国学院） 纠错

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

SmartMLOps Studio: Design of an LLM-Integrated IDE with Automated MLOps Pipelines for Model Development and Monitoring

Jiawei Jin, Yingxin Su, Xiaotong Zhu

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

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） 纠错

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

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） 纠错

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

Comments 39 pages

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

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） 纠错

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

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. 纠错

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

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） 纠错

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

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） 纠错

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)

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

Daniel M. Yellin

机构 * post.runi.ac.il（runi学院） 纠错

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

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） 纠错

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

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） 纠错

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)

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） 纠错

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

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） 纠错

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

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

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） 纠错

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

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） 纠错

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

Comments Pre-print IAAA workshop submission

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） 纠错

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

Comments NAACL2025 Tutorial

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

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） 纠错

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

Comments Accepted by CIKM' 25

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） 纠错

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

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） 纠错

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

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） 纠错

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

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） 纠错

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

Comments EMNLP 2025 Findings