Exploring the Reasoning Depth of Small Language Models in Software Architecture: A Multidimensional Evaluation Framework Towards Software Engineering 2.0
Faculty of Computer Science and Engineering Ho Chi Minh City University of Technology (HCMUT), VNU-HCM（胡志明市理工大学计算机科学与工程系）；The Business School RMIT University（皇家墨尔本理工大学商学院）
Ha Vo, Nhut Tran, Khang Vo, Phat T. Tran-Truong, Son Ha
In the era of "Software Engineering 2.0" (SE 2.0), where intelligent agents collaborate with human engineers, Generative AI is advancing beyond code generation into Software Architecture (SA). While Large Language Models (LLMs) demonstrate superior capabilities, computational costs and data privacy concerns drive interest in Small Language Models (SLMs) with fewer than 7 billion parameters. However, the reasoning limits of these resource-constrained models remain unexplored. This study benchmarks 10 state-of-the-art SLMs on Architectural Decision Records generation, introducing a multi-dimensional framework evaluating Technical Compliance and Semantic Diversity. Our empirical results reveal a significant reasoning gap: models above the 3B-parameter threshold demonstrate robust zero-shot capabilities, while sub-2B models show the strongest BERTScore gains from Fine-Tuning, though compliance improvements are not guaranteed. Contrary to assumptions regarding context saturation, Few-Shot prompting serves as a highly effective calibration mechanism for select mid-sized models with short context windows. Furthermore, high semantic diversity in off-the-shelf small models often correlates with hallucination rather than productive exploration. These findings establish a rigorous baseline for deploying sustainable, locally hosted architectural assistants.
Hidden Figures in Software Engineering: A Replication Study Exploring Undergraduate Software Students' Awareness of Distinguished Scientists from Underrepresented Groups
Exploring Statistical Change Point Detection Techniques for Performance Anomaly Detection at Mozilla
Concordia University（康考迪亚大学）；Mozilla；Chalmers University of Technology and the University of Gothenburg（查尔姆斯理工大学和哥德堡大学）；Eindhoven University of Technology（埃因霍温理工大学）
本文针对 Mozilla 性能异常检测中高误报和漏报问题，评估了 25 种变点检测方法和 15 种集成方法，基于人工标注的真实数据集发现集成投票策略在 F1 分数上提升 11%，并已集成到 Mozilla 系统。
Exploring CoCo Challenges in ML Engineering Teams: Insights From the Semiconductor Industry
Chair of Software Engineering, TUM School of Computation, Information and Technology, Technical University of Munich（慕尼黑技术大学计算、信息与技术学院软件工程系）；Business School, Pforzheim University（弗劳恩霍夫大学商学院）；Software and Sustainability (S2) Group, Vrije Universiteit Amsterdam（阿姆斯特丹自由大学软件与可持续性（S2）组）
Exploring the Use of ChatGPT by Computer Science Students in Software Development: Applications, Ethical Considerations, and Insights for Engineering Education
From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
School of Electrical and Computer Engineering, The University of Sydney（悉尼大学电气与计算机工程学院）；University at Buffalo, SUNY（纽约州立大学布法罗分校）；University of Chicago（芝加哥大学）
