Software Engineering Papers

Neurosymbolic Auditing of Natural-Language Software Requirements Bethel Hall, William Eiers arxiv.org/abs/2605.13817 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

(How) Do Large Language Models Understand High-Level Message Sequence Charts? Mohammad Reza Mousavi arxiv.org/abs/2605.13773 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙾]

SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems Hongji Pu, Xinyuan Song, Liang Zhao arxiv.org/abs/2605.13716 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙼𝙰] 💬Code: github.com/Hik289/SkillOp…

Scalable Deductive Verification of Data-Level Parallel Programs Lars B. van den Haak, Anton Wijs, Marieke Huisman arxiv.org/abs/2605.13616 [𝚌𝚜.𝚂𝙴]

SieveFL: Hierarchical Runtime-Aware Pruning for Scalable LLM-Based Fault Localization Mahdi Farzandway, Fatemeh Ghassemi arxiv.org/abs/2605.13491 [𝚌𝚜.𝚂𝙴]

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents Hailin Zhong, Shengxin Zhu arxiv.org/abs/2605.13357 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code Hengzhi Ye, Fengyuan Ran, Weiwei Xu, Minghui Zhou arxiv.org/abs/2605.13280 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Robust Mutation Analysis of Quantum Programs Under Noise Sophie Fortz, Eñaut Mendiluze Usandizaga, Shaukat Ali, Paolo Arcaini, Mohammad Reza Mousavi arxiv.org/abs/2605.13279 [𝚌𝚜.𝚂𝙴]

ReproScore: Separating Readiness from Outcome in Research Software Reproducibility Assessment Sheeba Samuel, Daniel Mietchen, Jungsan Kim, Waqas Ahmed, Martin Gaedke arxiv.org/abs/2605.13275 [𝚌𝚜.𝚂𝙴]

UIBenchKit: A unified toolkit for design-to-code model evaluation Chinh T. Le, Trevor Ong Yee Siang, Jingyu Xiao, Yuxuan Wan, Yintong Huo arxiv.org/abs/2605.13141 [𝚌𝚜.𝚂𝙴]

SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle Hao Guan, Lingyue Fu, Shao Zhang, Yaoming Zhu, Kangning Zhang, Lin Qiu, Xunliang Cai, Xuezhi Cao, Weiwen Liu, Weinan Zhang, Yong Yu arxiv.org/abs/2605.13139 [𝚌𝚜.𝚂𝙴]

Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study Nils Loose, Joseph Bienhüls, Kristoffer Hempel, Felix Mächtle, Thomas Eisenbarth arxiv.org/abs/2605.13138 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙻𝙶]

Protocol-Driven Development: Governing Generated Software Through Invariants and Evidence Jun He, Deying Yu arxiv.org/abs/2605.12981 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation Priyam Sahoo, Gaurav Mittal, Xiaomin Li, Shengjie Ma, Benjamin Steenhoek, Pingping Lin, Yu Hu arxiv.org/abs/2605.12925 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Project Life Cycles in Open-Source Software Sanjiv Das, Andrii Ieroshenko, Piyush Jain, David Qiu, Michael Chin, Brian Granger arxiv.org/abs/2605.12738 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝚂𝙸]

Finding a Crab in the C: Assured Translation via Comparative Symbolic Execution Caleb Helbling, Graham Leach-Krouse, Michael Crystal arxiv.org/abs/2605.12731 [𝚌𝚜.𝚂𝙴]

Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis Jacqueline L. Mitchell, Chao Wang arxiv.org/abs/2605.12694 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙿𝙻]

User Reviews as a Source for Usability Requirements: A Precursor Study on Using Large Language Models Cedric Wellhausen, Laura Reinhardt, Kurt Schneider arxiv.org/abs/2605.12657 [𝚌𝚜.𝚂𝙴]

Fine-Tuning Models for Automated Code Review Feedback Smitha S Kumar, Michael A Lones, Manuel Maarek, Hind Zantout arxiv.org/abs/2605.12610 [𝚌𝚜.𝚂𝙴]

Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance Elias Calboreanu arxiv.org/abs/2605.12280 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸] 💬Submitted to MDPI Software, Special Issue on Software Reliability, Security and Quality Assurance