arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

代码大模型 / AI 编程

代码生成、软件工程智能体、程序修复、测试生成和开发者工具。

共收录 291 信号源:cs.SE, cs.CL, cs.AI, cs.LG, cs.PL

1. 测试生成 291 篇

2506.02954 2026-04-17 cs.SE 74%

Mutation-Guided Unit Test Generation with a Large Language Model

基于大语言模型的突变指导单元测试生成

Guancheng Wang, Qinghua Xu, Lionel Briand, Kui Liu

专题命中 测试生成 :unit test generation(title);分类 cs.SE

AI总结 本文提出MUTGEN方法,利用突变反馈提升测试覆盖率,优于EvoSuite和传统提示方法,在突变分数上表现更优,并探讨了LLM生成的局限性。

Comments Accepted in IEEE Transactions on Software Engineering

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06107 2026-03-09 cs.SE 74%

Real-World Fault Detection for C-Extended Python Projects with Automated Unit Test Generation

面向C扩展Python项目的现实世界故障检测:自动化单元测试生成

Lucas Berg, Lukas Krodinger, Stephan Lukasczyk, Annibale Panichella, Gordon Fraser, Wim Vanhoof, Xavier Devroey

专题命中 测试生成 :unit test generation(title);分类 cs.SE

AI总结 本研究提出通过分离测试生成过程的生成与执行阶段,利用子进程执行技术提升C扩展Python项目中故障检测的覆盖率和准确性。

Comments Accepted at the 19th IEEE International Conference on Software Testing, Verification and Validation (ICST) 2026, Daejeon, Republic of Korea

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.08146 2026-02-11 cs.SE 74%

Test vs Mutant: Adversarial LLM Agents for Robust Unit Test Generation

测试与突变:对抗性LLM代理用于鲁棒性单元测试生成

Pengyu Chang, Yixiong Fang, Silin Chen, Yuling Shi, Beijun Shen, Xiaodong Gu

专题命中 测试生成 :unit test generation(title);分类 cs.SE

AI总结 AdverTest通过对抗性代理提升单元测试生成的鲁棒性,提高故障检测率和覆盖率

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15665 2025-11-20 cs.SE 74%

Quantum-Guided Test Case Minimization for LLM-Based Code Generation

Huixiang Zhang, Mahzabeen Emu

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

Comments This is a preprint version, full paper has been accepted in IEEE CASCON 2025 and will appear on lEEE Xplore

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09108 2025-10-13 cs.SE 74%

Constraint-Guided Unit Test Generation for Machine Learning Libraries

Lukas Krodinger, Altin Hajdari, Stephan Lukasczyk, Gordon Fraser

专题命中 测试生成 :unit test generation(title);分类 cs.SE

Comments Accepted for SSBSE 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08716 2025-10-13 cs.SE 74%

Search-based Hyperparameter Tuning for Python Unit Test Generation

Stephan Lukasczyk, Gordon Fraser

专题命中 测试生成 :unit test generation(title);分类 cs.SE

Comments Accepted to the 17th Symposium on Search-Based Software Engineering 2025 (SSBSE 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.18316 2025-07-25 cs.SE 74%

YATE: The Role of Test Repair in LLM-Based Unit Test Generation

Michael Konstantinou, Renzo Degiovanni, Jie M. Zhang, Mark Harman, Mike Papadakis

专题命中 测试生成 :unit test generation(title);分类 cs.SE

Comments 12 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.05256 2025-07-15 cs.SE 74%

IRFuzzer: Specialized Fuzzing for LLVM Backend Code Generation

Yuyang Rong, Zhanghan Yu, Zhenkai Weng, Stephen Neuendorffer, Hao Chen

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.10200 2025-01-20 cs.SE 74%

Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation

Azat Abdullin, Pouria Derakhshanfar, Annibale Panichella

专题命中 测试生成 :unit test generation(title);分类 cs.SE

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.11324 2024-08-22 cs.SE 74%

HITS: High-coverage LLM-based Unit Test Generation via Method Slicing

Zejun Wang, Kaibo Liu, Ge Li, Zhi Jin

专题命中 测试生成 :unit test generation(title);分类 cs.SE

Comments to be published in ASE 24' Research Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.06111 2024-02-12 cs.SE 74%

Observation-based unit test generation at Meta

Nadia Alshahwan, Mark Harman, Alexandru Marginean, Rotem Tal, Eddy Wang

专题命中 测试生成 :unit test generation(title);分类 cs.SE

Comments 12 pages, 8 figures, FSE 2024, Mon 15 - Fri 19 July 2024, Porto de Galinhas, Brazil

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.07518 2024-01-05 cs.SE 74%

Coverage Goal Selector for Combining Multiple Criteria in Search-Based Unit Test Generation

Zhichao Zhou, Yuming Zhou, Chunrong Fang, Zhenyu Chen, Xiapu Luo, Jingzhu He, Yutian Tang

专题命中 测试生成 :unit test generation(title);分类 cs.SE

Comments arXiv admin note: substantial text overlap with arXiv:2208.04096

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.06451 2023-10-11 cs.SE cs.SY eess.SY 74%

Energy Systems Test Case Discovery Enabled by Test Case Profile and Repository

Petra Raussi, Jirapa Kamsamrong, Alexandros Paspatis, Kai Heussen, Tesfaye Amare Zerihun, Edmund Widl, Filip Pröstl Andrén, Jawad H Kazmi, Thomas I. Strasser, Felipe Castro, Luigi Pellegrino

专题命中 测试生成 :repository(title);分类 cs.SE

Comments 2023 Open Source Modelling and Simulation of Energy Systems (OSMSES)

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.04096 2023-01-10 cs.SE 74%

Selectively Combining Multiple Coverage Goals in Search-Based Unit Test Generation

Zhichao Zhou, Yuming Zhou, Chunrong Fang, Zhenyu Chen, Yutian Tang

专题命中 测试生成 :unit test generation(title);分类 cs.SE

详情

展开后加载摘要…

URL PDF HTML 收藏
1906.01463 2019-06-05 cs.SE 74%

Bridging the Gap between Unit Test Generation and System Test Generation

Alexander Kampmann, Andreas Zeller

专题命中 测试生成 :unit test generation(title);分类 cs.SE

Comments this article supersedes arXiv:1812.07932

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13580 2025-09-01 cs.SE cs.AI 73%

LLM Test Generation via Iterative Hybrid Program Analysis

Sijia Gu, Noor Nashid, Ali Mesbah

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

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

Comments This paper has been accepted for publication in 2026 IEEE/ACM 48th International Conference on Software Engineering (ICSE 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.00418 2024-08-29 cs.SE cs.LG 73%

Using Large Language Models to Generate JUnit Tests: An Empirical Study

Mohammed Latif Siddiq, Joanna C. S. Santos, Ridwanul Hasan Tanvir, Noshin Ulfat, Fahmid Al Rifat, Vinicius Carvalho Lopes

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

Comments Accepted in Research Track of The 28th International Conference on Evaluation and Assessment in Software Engineering (EASE 2024)

Journal ref The 28th International Conference on Evaluation and Assessment in Software Engineering (EASE), 2024, 313-322

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.05052 2021-10-12 cs.CV 71%

LSC-GAN: Latent Style Code Modeling for Continuous Image-to-image Translation

Qiusheng Huang, Xueqi Hu, Li Sun, Qingli Li

专题命中 测试生成 :code model(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.03136 2025-09-26 cs.CL 70%

Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

Yinjie Wang, Ling Yang, Ye Tian, Ke Shen, Mengdi Wang

机构 * University of Chicago(芝加哥大学) Princeton University(普林斯顿大学) Peking University(北京大学) ByteDance Seed(字节跳动种子)

专题命中 测试生成 :code generation(abstract);unit test generation(abstract);分类 cs.CL

Comments NeurIPS 2025 Spotlight. Project: https://github.com/Gen-Verse/CURE

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.11532 2024-12-23 cs.SE cs.CR 70%

CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph

Hanxiang Xu, Wei Ma, Ting Zhou, Yanjie Zhao, Kai Chen, Qiang Hu, Yang Liu, Haoyu Wang

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

Comments 12 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.13669 2023-10-23 cs.LG cs.AI cs.CL cs.PL 70%

Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis

Philip John Gorinski, Matthieu Zimmer, Gerasimos Lampouras, Derrick Goh Xin Deik, Ignacio Iacobacci

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

Comments 9 pages + 4 pages appendix; 4 Figures, 4 Tables, 1 Algorithm; Accepted to Findings of EMNLP 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
1810.10614 2022-02-03 cs.SE 70%

Alleviating Patch Overfitting with Automatic Test Generation: A Study of Feasibility and Effectiveness for the Nopol Repair System

Zhongxing Yu, Matias Martinez, Benjamin Danglot, Thomas Durieux, Martin Monperrus

专题命中 测试生成 :program repair(abstract);repository(abstract);分类 cs.SE

Journal ref Empirical Software Engineering (Springer), 2018

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22883 2026-07-28 cs.SE cs.AI cs.LG 新提交 67%

Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests

评估和减轻大语言模型生成单元测试中错误代码的误导效应

Junda Zhao, Shurui Zhou, Eldan Cohen

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

AI总结 研究大语言模型生成单元测试时错误代码的误导效应,提出新指标衡量,分析其双重影响,引入基于规范的单元测试生成范式,有效减少误导性测试,增加有效测试,改善测试生成管道,适用于各类代码。

Comments 24 pages, 7 figures, 12 tables. Accepted at ISSTA 2026; to appear in Proceedings of the ACM on Software Engineering (PACMSE), Vol. 3, No. ISSTA, Article ISSTA113

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11950 2026-07-09 cs.SE cs.AI cs.CL cs.CR 版本更新 67%

AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection

AnyPoC:用于可扩展LLM基于Bug检测的通用证明-概念测试生成

Zijie Zhao, Chenyuan Yang, Weidong Wang, Yihan Yang, Ziqi Zhang, Lingming Zhang

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

专题命中 测试生成 :coding agent(abstract);分类 cs.SE、cs.CL、cs.AI

AI总结 AnyPoC通过多代理框架生成可执行的证明-概念测试,以验证候选Bug报告,提升自动化Bug检测的实用性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.06241 2026-04-09 cs.CR 67%

ZitPit: Consumer-Side Admission Control for Agentic Software Intake

ZitPit:面向代理软件摄入的消费者侧准入控制

Jepson Taylor, Chris Brousseau, Jordan Hildebrandt, Kelli Quinn

专题命中 测试生成 :repository(abstract);coding agent(abstract)

AI总结 ZitPit通过严格边界控制,确保首次见到的外部工件成为持久政策事件,统一了工件准入、仓库开放状态、能力范围执行和持久政策记录,提升代理工作流的安全性。

Comments 6 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05159 2026-04-08 cs.SE cs.AI cs.CL 67%

Planning to Explore: Curiosity-Driven Planning for LLM Test Generation

规划以探索:基于好奇心的规划用于LLM测试生成

Alfonso Amayuelas, Firas Laakom, Piotr Piękos, Wenyi Wang, Yifan Xu, Yuhui Wang, Jürgen Schmidhuber, William Wang

机构 * University of California, Santa Barbara(加州大学圣塔芭芭拉分校) King Abdullah University of Science and Technology(阿卜杜拉国王科技大学)

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

AI总结 本文提出CovQValue方法,通过将覆盖地图反馈给LLM生成多样化计划,并利用LLM估计的Q值选择最信息量的计划,以平衡即时分支发现与未来可达性,优于贪心策略,在测试生成任务中取得更高覆盖率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07449 2026-03-10 cs.DB cs.AI cs.CL cs.IR cs.LG 67%

Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System

Dial:一种基于知识的方言特定自然语言到SQL系统

Xiang Zhang, Hongming Xu, Le Zhou, Wei Zhou, Xuanhe Zhou, Guoliang Li, Yuyu Luo, Changdong Liu, Guorun Chen, Jiang Liao, Fan Wu

机构 * Tsinghua University(清华大学) China Telecom Corporation Ltd. Shanghai Branch(中国电信股份有限公司上海分公司) Shanghai Jiao Tong University(上海交通大学)

专题命中 测试生成 :repository(abstract);分类 cs.CL、cs.AI、cs.LG

AI总结 Dial提出一种基于知识的方言特定自然语言到SQL系统,通过逻辑查询规划、知识库和执行驱动调试提升翻译准确性和方言特征覆盖度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21997 2026-02-26 cs.SE cs.AI cs.LG 67%

Enhancing LLM-Based Test Generation by Eliminating Covered Code

通过消除已覆盖代码增强基于LLM的测试生成

WeiZhe Xu, Mengyu Liu, Fanxin Kong

机构 * University of Notre Dame(诺丁汉大学) Washington State University(华盛顿州立大学)

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

AI总结 本文提出一种基于LLM的单元测试生成方法,通过上下文检索和迭代测试生成与代码消除,提升复杂方法的测试覆盖率。

Comments 9 pages, 4 figures, supplementary material included

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06821 2026-01-15 cs.CL cs.AI cs.SE 67%

Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems

LLMs能否生成可靠的测试用例生成器?对竞赛级编程问题的研究

Yuhan Cao, Zian Chen, Kun Quan, Ziliang Zhang, Yu Wang, Xiaoning Dong, Yeqi Feng, Guanzhong He, Jingcheng Huang, Jianhao Li, Yixuan Tan, Jiafu Tang, Yilin Tang, Junlei Wu, Qianyu Xiao, Can Zheng, Shouchen Zhou, Yuxiang Zhu, Yiming Huang, Tianxing He

机构 * Shanghai Qi Zhi Institute(上海启智研究院) ShanghaiTech University(上海科技大学) Wuhan University(武汉大学) Fuzhou University(福州大学) Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所) Tsinghua University(清华大学) Huazhong University of Science and Technology(华中科技大学) Nanjing University(南京大学) Beijing University of Posts and Telecommunications(北京邮电大学) Peking University(北京大学)

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

AI总结 本文研究LLMs在生成竞赛级编程问题测试用例生成器方面的能力,提出TCGBench基准测试,并通过实验发现LLMs在生成针对性测试用例以暴露代码缺陷方面存在不足。

Comments 37 pages, 22 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.06185 2026-01-13 cs.SE cs.AI cs.CL 67%

Attention Mechanism and Heuristic Approach: Context-Aware File Ranking Using Multi-Head Self-Attention

注意力机制与启发式方法:基于多头自注意力的上下文感知文件排序

Pradeep Kumar Sharma, Shantanu Godbole, Sarada Prasad Jena, Hritvik Shrivastava

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

AI总结 本文提出基于多头自注意力机制的上下文感知文件排序方法,通过动态调整特征重要性提升召回率,改进仓库感知的努力估计

详情

展开后加载摘要…

URL PDF HTML 收藏