代码大模型 / AI 编程

Designing Empirical Studies on LLM-Based Code Generation: Towards a Reference Framework

Nathalia Nascimento, Everton Guimaraes, Paulo Alencar

机构 * The Pennsylvania State University（宾夕法尼亚州立大学） ； University of Waterloo（多伦多大学） 纠错

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

Comments 5 pages

LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design

Amir Sadikov

机构 * Amir Sadikov（阿米尔·萨迪科夫） 纠错

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

Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models

Runchu Tian, Junxia Cui, Xueqiang Xu, Feng Yao, Jingbo Shang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of California San Diego（加州大学圣地亚哥分校） 纠错

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

Comments 17 pages, 8 figures. Work in progress

SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design

Zeng Wang, Minghao Shao, Rupesh Karn, Likhitha Mankali, Jitendra Bhandari, Ramesh Karri, Ozgur Sinanoglu, Muhammad Shafique, Johann Knechtel

机构 * NYU Tandon School of Engineering（纽约大学Tandon工程学院） ； NYU Abu Dhabi（纽约大学阿布扎克分校） 纠错

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

GUISpector: An MLLM Agent Framework for Automated Verification of Natural Language Requirements in GUI Prototypes

Kristian Kolthoff, Felix Kretzer, Simone Paolo Ponzetto, Alexander Maedche, Christian Bartelt

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

Bamboo: LLM-Driven Discovery of API-Permission Mappings in the Android Framework

Han Hu, Wei Minn, Yonghui Liu, Jiakun Liu, Ferdian Thung, Terry Yue Zhuo, Lwin Khin Shar, Debin Gao, David Lo

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

LLMalMorph: On The Feasibility of Generating Variant Malware using Large-Language-Models

Md Ajwad Akil, Adrian Shuai Li, Imtiaz Karim, Arun Iyengar, Ashish Kundu, Vinny Parla, Elisa Bertino

专题命中 代码生成 ：code generation(abstract)

GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization

Jingzhi Gong, Yixin Bian, Luis de la Cal, Giovanni Pinna, Anisha Uteem, David Williams, Mar Zamorano, Karine Even-Mendoza, W. B. Langdon, Hector Menendez, Federica Sarro

机构 * University of Leeds（利兹大学） ； TurinTech AI（都灵科技AI） ； Harbin Normal University（哈尔滨师范大学） ； Universidad Politécnica de Madrid（马德里理工大学） ； University of Trieste（特里este大学） ； King’s College London（伦敦国王学院） ； University College London（伦敦大学学院） 纠错

专题命中 软件智能体 ：coding agent(abstract)；分类 cs.SE、cs.AI

Comments Accepted by SSBSE'25 Challenge Track

Back to the Basics: Rethinking Issue-Commit Linking with LLM-Assisted Retrieval

Huihui Huang, Ratnadira Widyasari, Ting Zhang, Ivana Clairine Irsan, Jieke Shi, Han Wei Ang, Frank Liauw, Eng Lieh Ouh, Lwin Khin Shar, Hong Jin Kang, David Lo

专题命中 软件智能体 ：repository(abstract)；分类 cs.SE

Extracting Conceptual Knowledge to Locate Software Issues

Ying Wang, Wenjun Mao, Chong Wang, Zhenhao Zhou, Yicheng Zhou, Wenyun Zhao, Yiling Lou, Xin Peng

专题命中 软件智能体 ：repository(abstract)；分类 cs.SE

REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement

Anvith Pabba, Simin Chen, Alex Mathai, Anindya Chakraborty, Baishakhi Ray

专题命中 程序修复 ：program repair(title,abstract)；repository(abstract)；分类 cs.SE

Comments We also open source our code at https://anonymous.4open.science/r/SemAgent-7B2F/README.md

LLM Chemistry Estimation for Multi-LLM Recommendation

Huascar Sanchez, Briland Hitaj

机构 * Computer Science Laboratory（计算机科学实验室） ； SRI International（SRI国际） 纠错

专题命中 程序修复 ：program repair(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 20 pages, 5 figures, 5 tables

PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecasting

Yiming Niu, Jinliang Deng, Yongxin Tong

机构 * School of Computer Science and Engineering（计算机科学与工程学院） ； Beihang University（北航） ； Department of Computer Science and Engineering（计算机科学与工程系） ； The Hong Kong University of Science and Technology（香港科学与技术大学） 纠错

专题命中 程序修复 ：repository(abstract)；分类 cs.AI、cs.LG

HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing

Yukai Zhao, Menghan Wu, Xing Hu, Xin Xia

机构 * School of Software Technology, Zhejiang University, Ningbo, China（软件技术学院，浙江大学，宁波，中国） ； The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China（区块链与数据安全国家重点实验室，浙江大学，杭州，中国） 纠错

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

Comments Accepted by ASE25

Program Synthesis Benchmark for Visual Programming in XLogoOnline Environment

Chao Wen, Jacqueline Staub, Adish Singla

专题命中 代码评测 ：program synthesis(title,abstract)；分类 cs.AI

Comments ACL'25 paper

Exploring the Power of Diffusion Large Language Models for Software Engineering: An Empirical Investigation

Jingyao Zhang, Tianlin Li, Xiaoyu Zhang, Qiang Hu, Bin Shi

专题命中 代码评测 ：code generation(abstract)；program repair(abstract)；分类 cs.SE

What Shapes a Creative Machine Mind? Comprehensively Benchmarking Creativity in Foundation Models

Zicong He, Boxuan Zhang, Weihao Liu, Ruixiang Tang, Lu Cheng

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Rutgers University（罗格斯大学） ； University of Illinois Chicago（伊利诺伊大学香槟分校） 纠错

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

Comments 22 pages

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents

Yanjie Li, Yiming Cao, Dong Wang, Bin Xiao

机构 * Computing Department of Hong Kong Polytechnic University（香港理工大学计算机系） ； Computing Department, The Hong Kong Polytechnic University（香港理工大学计算机系） 纠错

专题命中 代码评测 ：repository(abstract)；分类 cs.AI

Comments 13 pages, 8 figures. Submitted to IEEE Transactions on Information Forensics & Security

A Unified Optimization Framework for Multiclass Classification with Structured Hyperplane Arrangements

Víctor Blanco, Harshit Kothari, James Luedtke

机构 * Institute of Mathematics (IMAG), Universidad de Granada（格拉纳达大学数学研究所） ； Dept. Industrial & Systems Engineering, University of Wisconsin-Madison（威斯康星大学麦迪逊分校工业与系统工程系） 纠错

专题命中 仓库级理解 ：repository(abstract)；分类 cs.LG

Comments 28 pages, 2 tables, 9 figures

EEG-based AI-BCI Wheelchair Advancement: A Brain-Computer Interfacing Wheelchair System Using Deep Learning Approach

Biplov Paneru, Bishwash Paneru, Bipul Thapa, Khem Narayan Poudyal

专题命中 仓库级理解 ：repository(abstract)；分类 cs.AI

Comments The paper contains the outdated data as well as incoconsistent results. Much work is required for its revision and republishing

A First Look at the Lifecycle of DL-Specific Self-Admitted Technical Debt

Gilberto Recupito, Vincenzo De Martino, Dario Di Nucci, Fabio Palomba

专题命中 仓库级理解 ：repository(abstract)；分类 cs.SE

Comments Accepted at the International Workshop of Software Quality Assurance for Artificial Intelligence 2025 (SQA4AI), Montréal, Canada

Open-source FDTD solvers: The applicability of Elecode, gprMax and MEEP for simulations of lightning EM fields

Hannes Kohlmann, Dmitry Kuklin, Farhad Rachidi, Wolfgang Schulz

专题命中 仓库级理解 ：repository(abstract)

Comments 6 pages, 5 figures, conference CIGRE ICLPS-SIPDA 2013

Linear programming sensitivity measured by the optimal value worst-case analysis

Milan Hladík

专题命中 仓库级理解 ：repository(abstract)

Making high-order asymptotics practical: correcting goodness-of-fit test for astronomical count data

Xiaoli Li, Yang Chen, Xiao-Li Meng, David van Dyk, Massimiliano Bonamente, Vinay Kashyap

专题命中 仓库级理解 ：repository(abstract)

We've Got You Covered: Type-Guided Repair of Incomplete Input Generators

Patrick LaFontaine, Zhe Zhou, Ashish Mishra, Suresh Jagannathan, Benjamin Delaware

专题命中 程序分析与验证 ：program repair(abstract)；分类 cs.PL

Comments Extended version of OOPSLA 2025 paper