Related papers: Programming with Pixels: Can Computer-Use Agents d…
Software Engineering concepts such as version control, continuous integration, and unit testing are often not presented in college computer science curriculums until the third year of study, after completing several semesters of programming…
[Context] Engineering Artificial Intelligence (AI) software is a relatively new area with many challenges, unknowns, and limited proven best practices. Big companies such as Google, Microsoft, and Apple have provided a suite of recent…
Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of…
Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as…
Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on natural language instructions. The increasing accuracy of…
Peer review is the main mechanism by which the software engineering community assesses the quality of scientific results. However, the rapid growth of paper submissions in software engineering venues has outpaced the availability of…
Programming by example (PBE) is an emerging programming paradigm that automatically synthesizes programs specified by user-provided input-output examples. Despite the convenience for end-users, implementing PBE tools often requires strong…
Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting and limited generalization. To address this, we propose a novel scaling paradigm that shifts the…
Requirements and code, in conventional software engineering wisdom, belong to entirely different worlds. Is it possible to unify these two worlds? A unified framework could help make software easier to change and reuse. To explore the…
It has been 50 years since the term software engineering was coined in 1968 at a NATO conference. The field should be relatively mature by now, with most established universities covering core software engineering topics in their Computer…
Graphical User Interface (GUI) agents offer cross-platform solutions for automating complex digital tasks, with significant potential to transform productivity workflows. However, their performance is often constrained by the scarcity of…
Self-adaptive robotic systems operate autonomously in dynamic and uncertain environments, requiring robust real-time monitoring and adaptive behaviour. Unlike traditional robotic software with predefined logic, self-adaptive robots exploit…
When teaching Programming and Software Engineering in Bachelor's Degree programs, the emphasis on creating functional software projects often overshadows the focus on software quality, a trend that aligns with ACM curricula recommendations.…
Geospatial Copilots unlock unprecedented potential for performing Earth Observation (EO) applications through natural language instructions. However, existing agents rely on overly simplified single tasks and template-based prompts,…
In software applications, user models can be used to specify the profile of the typical users of the application, including personality traits, preferences, skills, etc. In theory, this would enable an adaptive application behavior that…
The advancement of large language models (LLMs) and code agents has demonstrated significant potential to assist software engineering (SWE) tasks, such as autonomous issue resolution and feature addition. Existing AI for software…
We present an empirical study of how far general-purpose coding agents -- without hardware-specific training -- can optimize hardware designs from high-level algorithmic specifications. We introduce an agent factory, a two-stage pipeline…
We ask whether agentic AI systems built for software engineering transfer to realistic hardware engineering. Existing hardware LLM benchmarks isolate sub-tasks but none jointly requires repository navigation, hierarchy-aware localization,…
Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques…
In the field of MLLM-based GUI agents, compared to smartphones, the PC scenario not only features a more complex interactive environment, but also involves more intricate intra- and inter-app workflows. To address these issues, we propose a…