Related papers: MaintainCoder: Maintainable Code Generation Under …
Comparing the quality of software written in different computer languages is required in a variety of scenarios, e.g. multi-language projects or application selection process among candidates in different languages. We focus on the…
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to…
Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating…
Modern software systems require code that is not only functional but also maintainable and well-structured. Although Large Language Models (LLMs) are increasingly used to automate software development, most studies focus on isolated,…
Code changes are an integral part of the software development process. Many code changes are meant to improve the code without changing its functional behavior, e.g., refactorings and performance improvements. Unfortunately, validating…
The software is changing rapidly with the invention of advanced technologies and methodologies. The ability to rapidly and successfully upgrade software in response to changing business requirements is more vital than ever. For the…
Software maintainability is essential for long-term success in the software industry. Despite widespread evidence of the high costs associated with poor maintainability, market pressure drives many organizations to prioritize short-term…
Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests,…
The focus on rapid software delivery inevitably results in the accumulation of technical debt, which, in turn, affects quality and slows future development. Yet, companies with a long history of rapid delivery exist. Our primary aim is to…
In the ever-shifting landscape of software engineering, we recognize the need for adaptation and evolution to maintain system dependability. As each software iteration potentially introduces new challenges, from unforeseen bugs to…
Multimodal large language models (MLLMs) have streamlined front-end interface development by automating code generation. However, these models also introduce challenges in ensuring code quality. Existing approaches struggle to maintain both…
Software sustainability is a key multifaceted non-functional requirement that encompasses environmental, social, and economic concerns, yet its integration into the development of Machine Learning (ML)-enabled systems remains an open…
Code generation tasks aim to automate the conversion of user requirements into executable code, significantly reducing manual development efforts and enhancing software productivity. The emergence of large language models (LLMs) has…
Recent advances in large language models have raised wide concern in generating abundant plausible source code without scrutiny, and thus tracing the provenance of code emerges as a critical issue. To solve the issue, we propose CodeMark, a…
The expansion of the open source community and the rise of large language models have raised ethical and security concerns on the distribution of source code, such as misconduct on copyrighted code, distributions without proper licenses, or…
Maintaining semantic consistency over extended text sequences remains a fundamental challenge in long-form text generation, where conventional training methodologies often struggle to prevent contextual drift and coherence degradation. A…
Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models. Although improving the robustness of code generation models is crucial to…
Automating the transformation of user interface (UI) designs into front-end code holds significant promise for accelerating software development and democratizing design workflows. While multimodal large language models (MLLMs) can…
While existing code large language models (code LLMs) exhibit impressive capabilities in code generation, their autoregressive sequential generation inherently lacks reversibility. This limitation hinders them from timely correcting…
Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their…