代码大模型 / AI 编程

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

Diversity driven Query Rewriting in Search Advertising

Akash Kumar Mohankumar, Nikit Begwani, Amit Singh

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

Comments Accepted in KDD 2021, 9 pages

Sionnx: Automatic Unit Test Generator for ONNX Conformance

Xinli Cai, Peng Zhou, Shuhan Ding, Guoyang Chen, Weifeng Zhang

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

ChatUniTest: A Framework for LLM-Based Test Generation

Yinghao Chen, Zehao Hu, Chen Zhi, Junxiao Han, Shuiguang Deng, Jianwei Yin

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

Comments This shorter version is accepted by the FSE 2024 Demonstrations Track, and the previous longer version titled "ChatUniTest: a ChatGPT-based automated unit test generation tool" can be found at arXiv:2305.04764v1

Scalable Distributed Simulation-Based Testing for Automated Driving Systems

面向自动驾驶系统的可扩展分布式基于仿真的测试

Christian Geller, Benedikt Haas, Lutz Eckstein

机构 * RWTH Aachen University（亚琛工业大学） ； Institute for Automotive Engineering (ika)（汽车工程研究所（ika）） 纠错

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

AI总结 本文提出一种DevOps驱动的端到端框架，在轻量级Kubernetes集群上自动化CARLA场景测试的构建与分布式执行，200个场景测试的端到端时间较基线提速超8倍，为ADS可扩展仿真测试提供支撑。

Comments 14 pages; Accepted to be published as part of the 17. Uni-DAS e.V. Workshop "Fahrerassistenz und automatisiertes Fahren", September 29-30, 2026

Auditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle Problem

在神谕问题下对LLM测试生成中反馈驱动演化的审计与分解

Yunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni

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

AI总结 该研究针对LLM测试生成中反馈驱动演化的神谕问题，通过多任务实验发现单一神谕会膨胀演化增益，提出审计-安慰剂协议以分离验证器人工制品等，为相关评估提供改进方案。

From Threat Intelligence to Detection: Knowledge-driven Enrichment and Template-based Rule Grounding for Automated Sigma Rule Generation

从威胁情报到检测：知识驱动的丰富化与基于模板的规则落地用于自动化Sigma规则生成

Sepehr Ghaffarzadegan, Boubakr Nour, Makan Pourzandi, Mourad Debbabi, Chadi Assi

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

AI总结 本研究设计了AUTOSIGMA，结合知识驱动丰富化等技术，将非结构化CTI报告自动生成Sigma规则，其在多项指标上优于其他方案。

Comments Submitted for publication and currently under review