New Software Engineering papers from arxiv.org: design tools, software metrics. Thank you to arXiv for use of its open access interoperability.
Joined April 2010
- Tweets 53,111
- Following 4
- Followers 2,470
- Likes 2
1,844 Photos and videos
Understanding the Rejection of Fixes Generated by Agentic Pull Requests β Insights from the AIDev Dataset
Mahmoud Abujadallah, Ali Arabat, Mohammed Sayagh
arxiv.org/abs/2606.13468 [ππ.ππ΄ ππ.π°πΈ]
1
73
Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests
Ali Arabat, Mohammed Sayagh
arxiv.org/abs/2606.13449 [ππ.ππ΄ ππ.π°πΈ]
2
63
Mining Architectural Quality Under Agentic AI Adoption: A Causal Study of Java Repositories
Oliver Aleksander Larsen, Mahyar T. Moghaddam
arxiv.org/abs/2606.13298 [ππ.ππ΄ ππ.π°πΈ]
1
87
ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm
Jiaxin Ai, Tao Hu, Xuemeng Yang, Shu Zou, Hairong Zhang, Daocheng Fu, Yu Yang, Hongbin Zhou, Nianchen Deng, Pinlong Cai, β¦
arxiv.org/abs/2606.13239 [ππ.ππ΄ ππ.π°πΈ ππ.π²π» ππ.π²π
]
102
The End of Code Review: Coding Agents Supersede Human Inspection
Martin Monperrus
arxiv.org/abs/2606.13175 [ππ.ππ΄]
1
3
118
The Rise of AI-Native Software Engineering: Implications for Practice, Education, and the Future Workforce
Mamdouh Alenezi
arxiv.org/abs/2606.12986 [ππ.ππ΄]
4
58
Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
Tingqiang Xu, Hangrui Zhou, Tianle Cai, Alex Gu, Kaifeng Lyu
arxiv.org/abs/2606.12864 [ππ.ππ΄ ππ.π°πΈ]
1
107
HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection
Luke Patterson, Li Wang, Adam Faulkner
arxiv.org/abs/2606.12620 [ππ.ππ΄ ππ.π°πΈ]
π¬Accepted to LREC 2026
1
46
Characterizing Tests in IoT Software: Practices, Challenges and Opportunities
Rufeng Chen, Hengcheng Zhu, Wuqi Zhang, Zixu Zhou, Lili Wei
arxiv.org/abs/2606.12592 [ππ.ππ΄]
1
68
Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study
Guangzong Cai, Ruiyin Li, Peng Liang, Zengyang Li, Mojtaba Shahin
arxiv.org/abs/2606.12231 [ππ.ππ΄ ππ.π°πΈ]
π¬Submitted to a Journal
1
1
5
154
Mind your key: An Empirical Study of LLM API Credential Leakage in iOS Apps
Pinran Gao, Lingxiang Wang, Ying Zhang, Fan Yang
arxiv.org/abs/2606.12212 [ππ.ππ΄ ππ.π²π]
50
Undefined Behavior in C and C : An Experiment With Desktop Use Cases
Jukka Ruohonen, Krzysztof Sierszecki
arxiv.org/abs/2606.12064 [ππ.ππ΄ ππ.π²π]
2
56
Exploration Structure in LLM Agents for Multi-File Change Localization
Akeela Darryl Fattha, Kia Ying Chua, Lingxiao Jiang, Laura Wynter
arxiv.org/abs/2606.11976 [ππ.ππ΄ ππ.π°πΈ]
93
Characterizing Software Aging in GPU-Based LLM Serving Systems
Domenico Cotroneo, Bojan Cukic
arxiv.org/abs/2606.11916 [ππ.ππ΄ ππ.π°πΈ]
59
Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production
Marc Alier Forment, Juanan Pereira, Francisco JosΓ© GarcΓa-PeΓ±alvo, MarΓa JosΓ© CasaΓ± Guerrero
arxiv.org/abs/2606.11869 [ππ.ππ΄ ππ.π°πΈ]
72
Enhancing LLM-Based Code Translation with Verified Multi-Semantic Representations
Yufu Wang, He Jiang, Hao Lin, Peiyu Zou, Ang Jia, Xiaochen Li, Zhilei Ren
arxiv.org/abs/2606.11863 [ππ.ππ΄]
68
How Requirements Quality Makes (or Breaks) Traceability Link Recovery
Tobias Hey, Julian Frattini
arxiv.org/abs/2606.11834 [ππ.ππ΄]
1
53
Understanding and Detecting Scalability Faults in Large-Scale Distributed Systems
Hao-Nan Zhu, Goodness Ayinmode, Cesar A. Stuardo, Haryadi S. Gunawi, Cindy Rubio-GonzΓ‘lez
arxiv.org/abs/2606.11815 [ππ.ππ΄]
55
Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis
Hongzhou Rao, Zikan Dong, Yanjie Zhao, Haodong Li, Haoyu Wang
arxiv.org/abs/2606.11755 [ππ.ππ΄]
1
3
80
SentTrack: Sentiment-Driven Bottleneck Detection in GitHub Issue Repositories
Xinyu Hu, Ali Behbahani, Daniel Moon, Yaren Dogan, Nasir U. Eisty
arxiv.org/abs/2606.11476 [ππ.ππ΄]
82