arXiv cs.SE Software Engineering

Salim Fares: Utilizing LLMs for Industrial Process Automation https://arxiv.org/abs/2602.23331 https://arxiv.org/pdf/2602.23331 https://arxiv.org/html/2602.23331

Zhang, Xiao, Wu, Zhao, Lin, Xu, Wang, Wang: LLM-Powered Silent Bug Fuzzing in Deep Learning Libraries via Versatile and Controlled Bug Transfer https://arxiv.org/abs/2602.23065 https://arxiv.org/pdf/2602.23065 https://arxiv.org/html/2602.23065

Haichuan Hu, Ye Shang, Guoqing Xie, Congqing He, Quanjun Zhang: CL4SE: A Context Learning Benchmark For Software Engineering Tasks https://arxiv.org/abs/2602.23047 https://arxiv.org/pdf/2602.23047 https://arxiv.org/html/2602.23047

Man Zhang, Tao Yue, Yihua He: Managing Uncertainty in LLM-based Multi-Agent System Operation https://arxiv.org/abs/2602.23005 https://arxiv.org/pdf/2602.23005 https://arxiv.org/html/2602.23005

Elisabeth Mo, Jefferson Seide Moll\'eri, Asle Fagerstr{\o}m: Productivity and Collaboration in Hybrid Agile Teams: An Interview Study https://arxiv.org/abs/2602.22835 https://arxiv.org/pdf/2602.22835 https://arxiv.org/html/2602.22835

Jiahong Xiang, Wenxiao He, Xihua Wang, Hongliang Tian, Yuqun Zhang: Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents https://arxiv.org/abs/2602.22764 https://arxiv.org/pdf/2602.22764 https://arxiv.org/html/2602.22764

Yuchong Xie, Kaikai Zhang, Yu Liu, Rundong Yang, Ping Chen, Shuai Wang, Dongdong She: RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling https://arxiv.org/abs/2602.22729 https://arxiv.org/pdf/2602.22729 https://arxiv.org/html/2602.22729

Xuefeng Li, Nir Ben-Israel, Yotam Raz, Belal Ahmed, Doron Serebro, Antoine Raux: RepoMod-Bench: A Benchmark for Code Repository Modernization via Implementation-Agnostic Testing https://arxiv.org/abs/2602.22518 https://arxiv.org/pdf/2602.22518 https://arxiv.org/html/2602.22518

Ikram Darif, Feifei Niu, Manel Abdellatif, Lionel C. Briand, Ramesh S., Arun Adiththan: Automating the Detection of Requirement Dependencies Using Large Language Models https://arxiv.org/abs/2602.22456 https://arxiv.org/pdf/2602.22456 https://arxiv.org/html/2602.22456

Saumendu Roy, Banani Roy, Chanchal Roy, Richard Bassey: XMENTOR: A Rank-Aware Aggregation Approach for Human-Centered Explainable AI in Just-in-Time Software Defect Prediction https://arxiv.org/abs/2602.22403 https://arxiv.org/pdf/2602.22403 https://arxiv.org/html/2602.22403

Cosmo Santoni: Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents https://arxiv.org/abs/2602.22402 https://arxiv.org/pdf/2602.22402 https://arxiv.org/html/2602.22402

Jiahao Zhang, Yifan Zhang, Kevin Leach, Yu Huang: EyeLayer: Integrating Human Attention Patterns into LLM-Based Code Summarization https://arxiv.org/abs/2602.22368 https://arxiv.org/pdf/2602.22368 https://arxiv.org/html/2602.22368

Oliver Karras: The Ethos of the PEERfect REVIEWer: Scientific Care and Collegial Welfare https://arxiv.org/abs/2602.22292 https://arxiv.org/pdf/2602.22292 https://arxiv.org/html/2602.22292

Oliver Karras, Amirreza Alasti, Lena John, Sushant Aggarwal, Y\"ucel Celik: EmpiRE-Compass: A Neuro-Symbolic Dashboard for Sustainable and Dynamic Knowledge Exploration, Synthesis, and Reuse https://arxiv.org/abs/2602.22276 https://arxiv.org/pdf/2602.22276 https://arxiv.org/html/2602.22276

[2026-02-27 Fri (UTC), 14 new articles found for csSE Software Engineering]

Kon, Pradeep, Chen, Ellis, Hunt, Wang, Yang, Thompson: SWE-Prot\'eg\'e: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents https://arxiv.org/abs/2602.22124 https://arxiv.org/pdf/2602.22124 https://arxiv.org/html/2602.22124

Eduardo Miranda: Visual Milestone Planning in a Hybrid Development Context https://arxiv.org/abs/2602.22076 https://arxiv.org/pdf/2602.22076 https://arxiv.org/html/2602.22076

Andr\'es Rodriguez, Juan Cruz Gardey, Alejandra Garrido: Detecting UX smells in Visual Studio Code using LLMs https://arxiv.org/abs/2602.22020 https://arxiv.org/pdf/2602.22020 https://arxiv.org/html/2602.22020

WeiZhe Xu, Mengyu Liu, Fanxin Kong: Enhancing LLM-Based Test Generation by Eliminating Covered Code https://arxiv.org/abs/2602.21997 https://arxiv.org/pdf/2602.21997 https://arxiv.org/html/2602.21997

Norman Peitek, Julia Hess, Sven Apel: From Restructuring to Stabilization: A Large-Scale Experiment on Iterative Code Readability Refactoring with Large Language Models https://arxiv.org/abs/2602.21833 https://arxiv.org/pdf/2602.21833 https://arxiv.org/html/2602.21833

Xinxue Zhu, Jiacong Wu, Xiaoyu Zhang, Tianlin Li, Yanzhou Mu, Juan Zhai, Chao Shen, Yang Liu: An Empirical Study of Bugs in Modern LLM Agent Frameworks https://arxiv.org/abs/2602.21806 https://arxiv.org/pdf/2602.21806 https://arxiv.org/html/2602.21806

Madhusudan Ghosh, Rishabh Gupta: An Evaluation of Context Length Extrapolation in Long Code via Positional Embeddings and Efficient Attention https://arxiv.org/abs/2602.21800 https://arxiv.org/pdf/2602.21800 https://arxiv.org/html/2602.21800

Selin Coban, Miguel Perez, Horst Lichter: Proto-ML: An IDE for ML Solution Prototyping https://arxiv.org/abs/2602.21734 https://arxiv.org/pdf/2602.21734 https://arxiv.org/html/2602.21734

Liu, Lin, Chang, Liu, Qi, Jiang, Huang, Dong: EditFlow: Benchmarking and Optimizing Code Edit Recommendation Systems via Reconstruction of Developer Flows https://arxiv.org/abs/2602.21697 https://arxiv.org/pdf/2602.21697 https://arxiv.org/html/2602.21697

Jiang, Wang, Dong, Fang, Duan, Wang, Hu, Yu, Jiang: AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch https://arxiv.org/abs/2602.21681 https://arxiv.org/pdf/2602.21681 https://arxiv.org/html/2602.21681

Man Zhang, Yunyang Li, Tao Yue: Uncertainty Modeling for SysML v2 https://arxiv.org/abs/2602.21641 https://arxiv.org/pdf/2602.21641 https://arxiv.org/html/2602.21641

Kangning Shen, Jingyuan Zhang, Chenxi Sun, Wencong Zeng, Yang Yue: Structurally Aligned Subtask-Level Memory for Software Engineering Agents https://arxiv.org/abs/2602.21611 https://arxiv.org/pdf/2602.21611 https://arxiv.org/html/2602.21611

Yuvraj Agrawal, Pallav Jain: From Ad-Hoc Scripts to Orchestrated Pipelines: Architecting a Resilient ELT Framework for Developer Productivity Metrics https://arxiv.org/abs/2602.21568 https://arxiv.org/pdf/2602.21568 https://arxiv.org/html/2602.21568

Clemens Pohle: AgenticTyper: Automated Typing of Legacy Software Projects Using Agentic AI https://arxiv.org/abs/2602.21251 https://arxiv.org/pdf/2602.21251 https://arxiv.org/html/2602.21251

[2026-02-26 Thu (UTC), 14 new articles found for csSE Software Engineering]