Software Engineering Papers

GapForge: Directed Compiler Fuzzing via Coverage-Gap Analysis Mingxuan Zhu, Qingyuan Liang, Junjie Chen, Zhihong Xue, Dan Hao arxiv.org/abs/2607.15762 [𝚌𝚜.𝚂𝙴]

Verified LLM-Driven Synthesis for Concept Design Alcino Cunha arxiv.org/abs/2607.15718 [𝚌𝚜.𝚂𝙴]

Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports Jingyi Chen, Songqiang Chen, Hengcheng Zhu, Jialun Cao, Jiasi Shen, Shing-Chi Cheung arxiv.org/abs/2607.15684 [𝚌𝚜.𝚂𝙴]

Two-Path Status Verification for Outbound Enterprise Messaging Pipelines: Webhook and Scheduled Polling Fallback Architecture Devam Gupta arxiv.org/abs/2607.15529 [𝚌𝚜.𝚂𝙴]

MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization Shaoxiong Zhan, Shi Hu, Boyu Feng, Hai Lin, Andrew Gong, Zhengda Zhou, Jiaying Zhou, Yunyun Hou, Hao Su, … arxiv.org/abs/2607.15205 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Navigating the Socio-Technical Complexity Challenge in Quantum Software Ecosystems Ronja Heikkinen, Santiago Núñez-Corrales, Vlad Stirbu arxiv.org/abs/2607.15135 [𝚌𝚜.𝚂𝙴]

Capturing and Exploiting Design Pattern Variability in Mobile Application Generation Ramón Peralta, Jose-Miguel Horcas arxiv.org/abs/2607.15099 [𝚌𝚜.𝚂𝙴]

Leaf: An Instrumentation-based Dynamic Analysis Framework for Rust Mohammad Omidvar Tehrani, Marco Gaboardi, Nick Sumner, Steven Y. Ko arxiv.org/abs/2607.15025 [𝚌𝚜.𝚂𝙴]

FirmPilot: Evidence-Guided Multi-Agent Environment Recovery for IoT Firmware Rehosting Yanbing Shen, Fan Zhang, Haitao Xu arxiv.org/abs/2607.14903 [𝚌𝚜.𝚂𝙴]

StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows Sizhong Qin, Yi Gu, Yao Jiang, Ao Cai, Changjian Zhou, Shaoxuan Shuai, Jiachang Wang, Tianhao Shen, Yueqiang Li, … arxiv.org/abs/2607.14896 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙼𝙰]

AI Prototyper: A Figma Plugin for Decomposition-Based GUI Prototyping with LLMs Tawatchai Salangsingha, Sami Ashkan, Md Zia Ullah, Iain McGregor arxiv.org/abs/2607.14830 [𝚌𝚜.𝚂𝙴]

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality Saima Afrin, Alessandro Midolo, Camilo Escobar-Velásquez, Mario Linares-Vásquez, Weiyuan Ding, Bowen Xu, … arxiv.org/abs/2607.14816 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

LLM-Driven Approach to Modeling Tool Interoperability in Automotive Domain Nenad Petrovic, Jiajie Zhang, Vahid Zolfaghari, Alois Knoll arxiv.org/abs/2607.14659 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Rethinking Issue Resolution for AI/ML Systems Ahmed Adnan, Mushfiqur Rahman, Antu Saha, Oscar Chaparro arxiv.org/abs/2607.14657 [𝚌𝚜.𝚂𝙴]

SYNAPSE: A Multi-LLM Orchestrated AI Tutor for Secure Software Development Education with Neurodivergent-First Design Giusy Ferrara, Ashkan Sami arxiv.org/abs/2607.14601 [𝚌𝚜.𝚂𝙴]

A Deterministic Binary Fingerprinting Framework with Zero-Trained Feature Extraction for Sparse Count Matrices Lei Zhao, Fujin Huang, Ling Kang, Quan Guo arxiv.org/abs/2607.14596 [𝚌𝚜.𝚂𝙴]

Predicting Human Visual Attention on Words in Source Code Chia-Yi Su, Collin McMillan arxiv.org/abs/2607.14535 [𝚌𝚜.𝚂𝙴]

Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution Harris Borman, Herman Wandabwa, Fusun Yu, Sandeepa Kannangara, Justin Liu, Anna Leontjeva, Ritchie Ng arxiv.org/abs/2607.14456 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

AI-Conducted Interviews in Empirical Software Engineering: An Experience Report Rohit Gheyi, Danyllo Albuquerque, Márcio Ribeiro, Mirko Perkusich arxiv.org/abs/2607.14452 [𝚌𝚜.𝚂𝙴]

Why Git Is the Memory Solution for the Agentic Development Lifecycle Frank Guo arxiv.org/abs/2607.14390 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙸𝚁]