Software Engineering

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety Xuan Chen, Lu Yan, Ruqi Zhang, Xiangyu Zhang arxiv.org/abs/2603.18245 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝚁]

Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought Zichen Xie, Wenxi Wang arxiv.org/abs/2603.18334 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

Where are the Hidden Gems? Applying Transformer Models for Design Discussion Detection Lawrence Arkoh, Daniel Feitosa, Wesley K. G. Assunção arxiv.org/abs/2603.18393 [𝚌𝚜.𝚂𝙴]

SQL-Commenter: Aligning Large Language Models for SQL Comment Generation with Direct Preference Optimization Lei Yu, Peng Wang, Jingyuan Zhang, Xin Wang, Jia Xu, Li Yang, Changzhi Deng, Jiajia Ma, Fengjun Zhang arxiv.org/abs/2603.18606 [𝚌𝚜.𝚂𝙴]

Green Architectural Tactics in ML-enabled Systems: An LLM-based Repository Mining Study Vincenzo De Martino, Silverio Martínez-Fernández, Fabio Palomba arxiv.org/abs/2603.18734 [𝚌𝚜.𝚂𝙴]

SpaceTime Programming: Live and Omniscient Exploration of Code and Execution Jean-Baptiste Döderlein, Djamel Eddine Khelladi, Mathieu Acher, Benoit Combemale arxiv.org/abs/2603.18735 [𝚌𝚜.𝚂𝙴]

Measuring and Exploiting Confirmation Bias in LLM-Assisted Security Code Review Dimitris Mitropoulos, Nikolaos Alexopoulos, Georgios Alexopoulos, Diomidis Spinellis arxiv.org/abs/2603.18740 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁]

The State of Generative AI in Software Development: Insights from Literature and a Developer Survey Vincent Gurgul, Robin Gubela, Stefan Lessmann arxiv.org/abs/2603.16975 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙴𝚃 𝚌𝚜.𝙷𝙲]

When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents Lu Yan, Xuan Chen, Xiangyu Zhang arxiv.org/abs/2603.17104 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

A Longitudinal Study of Usability in Identity-Based Software Signing Kelechi G. Kalu, Hieu Tran, Santiago Torres-Arias, Sooyeon Jeong, James C. Davis arxiv.org/abs/2603.17133 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝚁]

Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents Shuvendu K. Lahiri arxiv.org/abs/2603.17150 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙿𝙻]

Energy Flow Graph: Modeling Software Energy Consumption Saurabhsingh Rajput, Tushar Sharma arxiv.org/abs/2603.17162 [𝚌𝚜.𝚂𝙴]

Talk is Cheap, Logic is Hard: Benchmarking LLMs on Post-Condition Formalization I. S. W. B. Prasetya, Fitsum Kifetew, Davide Prandi arxiv.org/abs/2603.17193 [𝚌𝚜.𝚂𝙴]

Revisiting Vulnerability Patch Identification on Data in the Wild Ivana Clairine Irsan, Ratnadira Widyasari, Ting Zhang, Huihui Huang, Ferdian Thung, Yikun Li, Lwin Khin Shar, Eng Lieh Ouh, Hong Jin Kang, David Lo arxiv.org/abs/2603.17266 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝚁]

MLmisFinder: A Specification and Detection Approach of Machine Learning Service Misuses Hadil Ben Amor, Niruthiha Selvanayagam, Manel Abdellatif, Taher A. Ghaleb, Naouel Moha arxiv.org/abs/2603.17330 [𝚌𝚜.𝚂𝙴]

Bootstrapping Coding Agents: The Specification Is the Program Martin Monperrus arxiv.org/abs/2603.17399 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙻𝙶]

Requirements Volatility in Software Architecture Design: An Exploratory Case Study Sanja Aaramaa, Sandun Dasanayake, Markku Oivo, Jouni Markkula, Samuli Saukkonen arxiv.org/abs/2603.17648 [𝚌𝚜.𝚂𝙴]

From Symbol to Meaning: Ontological and Philosophical Reflections on Large Language Models in Information Systems Engineering José Palazzo Moreira de Oliveira arxiv.org/abs/2603.17659 [𝚌𝚜.𝚂𝙴]

CodeT5-RNN: Reinforcing Contextual Embeddings for Enhanced Code Comprehension Md Mostafizer Rahman, Ariful Islam Shiplu, Yutaka Watanobe, Md Faizul Ibne Amin, Syed Rameez Naqvi, Fang Liu arxiv.org/abs/2603.17821 [𝚌𝚜.𝚂𝙴]

FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair Ruize Ma, Yilei Jiang, Shilin Zhang, Zheng Ma, Yi Feng, Vincent Ng, Zhi Wang, Xiangyu Yue, Chuanyi Li, Lewei Lu arxiv.org/abs/2603.17826 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]