代码大模型 / AI 编程

HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning

Yujian Liu, Jiabao Ji, Yang Zhang, Wenbo Guo, Tommi Jaakkola, Shiyu Chang

机构 * UC Santa Barbara（加州大学圣巴巴拉分校） ； MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室） ； MIT CSAIL（麻省理工CSAIL） 纠错

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

Retrieval-Augmented Test Generation: How Far Are We?

Jiho Shin, Nima Shiri Harzevili, Reem Aleithan, Hadi Hemmati, Song Wang

机构 * York University（约克大学） 纠错

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

Comments 11 pages + reference. Accepted as Research Track Paper at ICSE'26

Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discovery

Bowen Wei

机构 * George Mason University（乔治·马歇尔大学） 纠错

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

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

Repair-R1: Better Test Before Repair

Haichuan Hu, Xiaochen Xie, Quanjun Zhang

机构 * Nanjing University of Science and Technology（南京理工大学） 纠错

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

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization

Sunay Joshi, Shayan Kiyani, George Pappas, Edgar Dobriban, Hamed Hassani

机构 * University of Pennsylvania（宾夕法尼亚大学） 纠错

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

Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

Yingkai Dong, Xiangtao Meng, Ning Yu, Zheng Li, Shanqing Guo

机构 * School of Cyber Science and Technology, Shandong University（山东大学网络科学与技术学院） ； Netflix Eyeline Studios ； State Key Laboratory of Cryptography and Digital Economy Security, Shandong University（山东大学密码与数字经济安全国家重点实验室） ； Shandong Key Laboratory of Artificial Intelligence Security, Shandong University（山东省人工智能安全重点实验室） 纠错

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

AI-Driven Tools in Modern Software Quality Assurance: An Assessment of Benefits, Challenges, and Future Directions

Ihor Pysmennyi, Roman Kyslyi, Kyrylo Kleshch

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

Comments 11 pages, 9 figures

Journal ref Technology Audit and Production Reserves, 3(2(83)), 44-54 (2025)

UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance

Yichuan Ma, Yunfan Shao, Peiji Li, Demin Song, Qipeng Guo, Linyang Li, Xipeng Qiu, Kai Chen

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

Comments work in progress

UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts

Bo Yang, Qingping Yang, Yingwei Ma, Runtao Liu

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

Dynamic Scaling of Unit Tests for Code Reward Modeling

Zeyao Ma, Xiaokang Zhang, Jing Zhang, Jifan Yu, Sijia Luo, Jie Tang

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

Comments Homepage: https://code-reward-model.github.io/

GenX: Mastering Code and Test Generation with Execution Feedback

Nan Wang, Yafei Liu, Chen Chen, Haonan Lu

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

CPP-UT-Bench: Can LLMs Write Complex Unit Tests in C++?

Vaishnavi Bhargava, Rajat Ghosh, Debojyoti Dutta

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

Large Language Models as a Tool for Mining Object Knowledge

Hannah YoungEun An, Lenhart K. Schubert

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

Examination of Code generated by Large Language Models

Robin Beer, Alexander Feix, Tim Guttzeit, Tamara Muras, Vincent Müller, Maurice Rauscher, Florian Schäffler, Welf Löwe

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

AutoTest: Evolutionary Code Solution Selection with Test Cases

Zhihua Duan, Jialin Wang

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

Transforming Software Development: Evaluating the Efficiency and Challenges of GitHub Copilot in Real-World Projects

Ruchika Pandey, Prabhat Singh, Raymond Wei, Shaila Shankar

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

Comments 13 pages, 8 figures

Large Language Models as Test Case Generators: Performance Evaluation and Enhancement

Kefan Li, Yuan Yuan

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

Breaking the Silence: the Threats of Using LLMs in Software Engineering

June Sallou, Thomas Durieux, Annibale Panichella

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

Comments Accepted at the ICSE'24 conference, NIER track

Taming the Beast: Fully Automated Unit Testing with Coyote C++

Sanghoon Rho, Philipp Martens, Seungcheol Shin, Yeoneo Kim

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

TheoremQA: A Theorem-driven Question Answering dataset

Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, Tony Xia

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

Comments Accepted to Main Conference of EMNLP 2023

PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs

Yixuan He, Xitong Zhang, Junjie Huang, Benedek Rozemberczki, Mihai Cucuringu, Gesine Reinert

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

Comments Accepted by LoG 2023. 27 pages in total

Spot: A Natural Language Interface for Geospatial Searches in OSM

Lynn Khellaf, Ipek Baris Schlicht, Julia Bayer, Ruben Bouwmeester, Tilman Miraß, Tilman Wagner

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

Comments To be published in the Proceedings of the OSM Science 2023

CAT-LM: Training Language Models on Aligned Code And Tests

Nikitha Rao, Kush Jain, Uri Alon, Claire Le Goues, Vincent J. Hellendoorn

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

Prompting Code Interpreter to Write Better Unit Tests on Quixbugs Functions

Vincent Li, Nick Doiron

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

Comments 13 pages (including appendices), 0 figures, 1 table. First authored by Vincent Li; edited by Nick Doiron

NeuRI: Diversifying DNN Generation via Inductive Rule Inference

Jiawei Liu, Jinjun Peng, Yuyao Wang, Lingming Zhang

专题命中 测试生成 ：program synthesis(abstract)；分类 cs.SE、cs.LG

TorchBench: Benchmarking PyTorch with High API Surface Coverage

Yueming Hao, Xu Zhao, Bin Bao, David Berard, Will Constable, Adnan Aziz, Xu Liu

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

CBMC: The C Bounded Model Checker

Daniel Kroening, Peter Schrammel, Michael Tautschnig

专题命中 测试生成 ：program synthesis(abstract)；分类 cs.SE、cs.PL

Comments Book chapter preview

Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers

Frederico Dias Souza, João Baptista de Oliveira e Souza Filho

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

Comments 14 pages, 6 figures. Published at Springer Neural Computing and Applications journal

Journal ref Neural Comput & Applic (2022)

Learning How to Search: Generating Effective Test Cases Through Adaptive Fitness Function Selection

Hussein Almulla, Gregory Gay

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

Comments Accepted, to appear in Empirical Software Engineering Journal