代码大模型 / AI 编程

Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go

Go-UT-Bench：用于基于LLM的Go语言单元测试生成的微调数据集

Yashshi Pipalani, Hritik Raj, Rajat Ghosh, Vaishnavi Bhargava, Debojyoti Dutta

机构 * Nutanix 纠错

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

AI总结 针对代码LLM训练数据不平衡问题，提出Go-UT-Bench数据集（5264对代码与单元测试），通过微调提升模型在Go语言单元测试生成任务上的性能，在超过75%的基准任务上优于基础模型。

Comments 9 pages, 5 figures

PR-Aware Automated Unit Test Generation: Challenges and Opportunities

PR感知的自动化单元测试生成：挑战与机遇

Vahid Haratian, Atakan Akar, Berk Çakar, Eray Tüzün

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

AI总结 本研究评估了EvoSuite和GPT-4o在拉取请求（PR）级别生成测试用例的能力，发现两者均难以有效生成捕获变更的测试，但EvoSuite优于GPT-4o，并指出智能体代码生成方法具有潜力。

Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation

幻觉到共识：多智能体LLM用于端到端JUnit测试生成

Qinghua Xu, Guancheng Wang, Lionel Briand, Kui Liu

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

AI总结 本文提出CANDOR框架，通过多智能体协作生成Java单元测试，利用共识策略减少幻觉并提升Oracle准确性，实验表明其在代码覆盖率和突变得分上优于现有方法。

Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging

通过自我调试合成文件级数据用于单元测试生成的链式思考

Ziyue Hua, Tianyu Chen, Yeyun Gong, Shuai Lu, Peng Cheng, Qinglin Zhu, Yibo He, Yingjie Fu, Wenpin Jiao, Wei Yang, Tao Xie

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

AI总结 通过自我调试合成文件级数据用于单元测试生成，提升测试生成质量与准确性。

Large Language Models for Unit Test Generation: Achievements, Challenges, and Opportunities

大语言模型用于单元测试生成：成就、挑战与机遇

Bei Chu, Yang Feng, Kui Liu, Zhaoqiang Guo, Yichi Zhang, Hange Shi, Zifan Nan, Baowen Xu

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

AI总结 大语言模型在单元测试生成中展现出优势，但面临语义理解不足和标准化不足等挑战，未来需发展自主测试代理与混合系统。

Comments 27 pages, 8 figures

Reflective Unit Test Generation for Precise Type Error Detection with Large Language Models

Chen Yang, Ziqi Wang, Yanjie Jiang, Lin Yang, Yuteng Zheng, Jianyi Zhou, Junjie Chen

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

Comments accepted in the research track of ASE 2025

CITYWALK: Enhancing LLM-Based C++ Unit Test Generation via Project-Dependency Awareness and Language-Specific Knowledge

Yuwei Zhang, Qingyuan Lu, Kai Liu, Wensheng Dou, Jiaxin Zhu, Li Qian, Chunxi Zhang, Zheng Lin, Jun Wei

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

Comments Preprint, to appear in the ACM Transactions on Software Engineering and Methodology (TOSEM)

Seed&Steer: Guiding Large Language Models with Compilable Prefix and Branch Signals for Unit Test Generation

Shuaiyu Zhou, Zhengran Zeng, Xiaoling Zhou, Rui Xie, Shikun Zhang, Wei Ye

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

TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark

Kush Jain, Gabriel Synnaeve, Baptiste Rozière

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

Less is More: On the Importance of Data Quality for Unit Test Generation

Junwei Zhang, Xing Hu, Shan Gao, Xin Xia, David Lo, Shanping Li

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

ASTER: Natural and Multi-language Unit Test Generation with LLMs

Rangeet Pan, Myeongsoo Kim, Rahul Krishna, Raju Pavuluri, Saurabh Sinha

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

Comments Accepted at ICSE-SEIP, 2025

What You See Is What You Get: Attention-based Self-guided Automatic Unit Test Generation

Xin Yin, Chao Ni, Xiaodan Xu, Xiaohu Yang

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

Comments Accepted By ICSE'25

LLM-based Unit Test Generation via Property Retrieval

Zhe Zhang, Xingyu Liu, Yuanzhang Lin, Xiang Gao, Hailong Sun, Yuan Yuan

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

On the Evaluation of Large Language Models in Unit Test Generation

Lin Yang, Chen Yang, Shutao Gao, Weijing Wang, Bo Wang, Qihao Zhu, Xiao Chu, Jianyi Zhou, Guangtai Liang, Qianxiang Wang, Junjie Chen

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

Comments Accepted by ASE 2024, Research Paper Track

CasModaTest: A Cascaded and Model-agnostic Self-directed Framework for Unit Test Generation

Chao Ni, Xiaoya Wang, Liushan Chen, Dehai Zhao, Zhengong Cai, Shaohua Wang, Xiaohu Yang

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

Comments 14 pages, 7 figures

No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation

Zhiqiang Yuan, Yiling Lou, Mingwei Liu, Shiji Ding, Kaixin Wang, Yixuan Chen, Xin Peng

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

Automatic Unit Test Generation for Deep Learning Frameworks based on API Knowledge

Arunkaleeshwaran Narayanan, Nima Shiri harzevili, Junjie Wang, Lin Shi, Moshi Wei, Song Wang

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

An Empirical Study of Automated Unit Test Generation for Python

Stephan Lukasczyk, Florian Kroiß, Gordon Fraser

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

Comments 51 pages, submitted to EMSE Special Issue on Advances in Search-Based Software Engineering. arXiv admin note: text overlap with arXiv:2007.14049

Pynguin: Automated Unit Test Generation for Python

Stephan Lukasczyk, Gordon Fraser

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

Comments 5 pages

CoCoFuzzing: Testing Neural Code Models with Coverage-Guided Fuzzing

Moshi Wei, Yuchao Huang, Jinqiu Yang, Junjie Wang, Song Wang

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

Automated Unit Test Generation for Python

Stephan Lukasczyk, Florian Kroiß, Gordon Fraser

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

Comments 15 pages, to be published in Proceedings of the 12th Symposium on Search-Based Software Engineering (SSBSE 2020)

Automated Regression Unit Test Generation for Program Merges

Tao Ji, Liqian Chen, Xiaoguang Mao, Xin Yi, Jiahong Jiang

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

A Multi-Agent Framework for Stateful Inference-Time Search

Arshika Lalan, Rajat Ghosh, Aditya Kolsur, Debojyoti Dutta

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Nutanix（Nutanix公司） 纠错

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

LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework

基于大型语言模型的Java自动化单元测试生成与评估：AgoneTest框架

Andrea Lops, Fedelucio Narducci, Azzurra Ragone, Michelantonio Trizio, Claudio Bartolini

机构 * University of Bari, Bari, Italy（巴里大学） 纠错

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

AI总结 AgoneTest框架通过标准化评估流程，评估大型语言模型生成的Java单元测试质量，展示其在覆盖率和缺陷检测上的表现，并探讨提示策略对测试质量的影响。

Comments Accepted at 40th IEEE/ACM International Conference on Automated Software Engineering

Impact of Code Context and Prompting Strategies on Automated Unit Test Generation with Modern General-Purpose Large Language Models

Jakub Walczak, Piotr Tomalak, Artur Laskowski

机构 * Lodz University of Technology（华沙理工大学） ； Comarch 纠错

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

A Study on the Improvement of Code Generation Quality Using Large Language Models Leveraging Product Documentation

Takuro Morimoto, Harumi Haraguchi

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

Comments 12 pages, 5 figures and 10 tables

Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation

Benjamin Steenhoek, Michele Tufano, Neel Sundaresan, Alexey Svyatkovskiy

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

Comments This work was intended as a replacement of arXiv:2310.02368 and any subsequent updates will appear there

Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing

Rabimba Karanjai, Aftab Hussain, Md Rafiqul Islam Rabin, Lei Xu, Weidong Shi, Mohammad Amin Alipour

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

CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks

Hongchao Jiang, Yiming Chen, Yushi Cao, Hung-yi Lee, Robby T. Tan

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

Comments Dataset is available at https://huggingface.co/datasets/mattymchen/codejudgebench

RLTF: Reinforcement Learning from Unit Test Feedback

Jiate Liu, Yiqin Zhu, Kaiwen Xiao, Qiang Fu, Xiao Han, Wei Yang, Deheng Ye

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

Comments Accepted by TMLR