대규모 언어 모델(LLM)은 코드 리팩토링 작업을 자동화하여 코드 품질을 향상시키는 데 효과적이며, 특히 구문 및 패턴 기반 코드 냄새를 줄이는 데 탁월하지만, 복잡한 디자인 문제 해결에는 개발자의 전문 지식이 여전히 필요합니다.
大規模言語モデルStarCoder2は、開発者が書いたコードと同じコードに対して、コードスメルの削減やコード品質の改善において、多くの場合、開発者よりも優れたパフォーマンスを発揮する。
Large Language Models (LLMs), specifically StarCoder2, demonstrate promising capabilities in automating code refactoring, often surpassing human developers in reducing code smells and improving certain code quality metrics, but still face challenges in replicating the contextual understanding and complex decision-making of experienced developers.
While promising for automating the laborious task of writing specifications for static verification tools, OpenAI's GPT models, even with advanced prompting techniques, still struggle to consistently generate fully correct and verifiable specifications in VeriFast for heap-manipulating C code.
本稿では、新しい大規模多言語コードデバッグベンチマークであるMDEVALを提案し、自動プログラム修復、コードレビュー、バグ識別の3つのタスクにおけるオープンソースモデルとクローズドソースモデルのデバッグ性能を評価した。
Continuous Analysis, an extension of DevOps practices, enhances the reproducibility of scientific research by incorporating version control, automated workflows, and comprehensive feedback mechanisms throughout the research lifecycle.
DevOps practices, particularly Continuous Integration/Continuous Delivery (CI/CD) and robust Source Code Management (SCM), significantly enhance R&D efficiency and software delivery success in large-scale enterprises, despite challenges such as cultural resistance and tool integration complexities.
Linux 核心回歸錯誤的修復時間比先前報告的要快,設備驅動程式是回歸錯誤最容易出現的子系統,但代碼審查和測試實務並不能解釋修復時間的差異。
While advanced language models demonstrate strong potential in software engineering tasks, the effectiveness of traditional prompt engineering techniques diminishes with their use, particularly for reasoning models.
본 논문은 교사의 디지털 성숙도를 측정하고 진단하기 위한 통합 모델(MUME)을 제안하고, 이 모델을 기반으로 한 진단 방법론 개발을 위한 예비 연구 결과를 제시합니다.