A new method enhances automated code review comments using reviewer experience.
Hong Yi Lin, Patanamon Thongtanunam, Christoph Treude
― 6 min read
Cutting edge science explained simply
A new method enhances automated code review comments using reviewer experience.
Hong Yi Lin, Patanamon Thongtanunam, Christoph Treude
― 6 min read
Examining prompt programming and its impact on software creation and user experience.
Jenny T. Liang, Melissa Lin, Nikitha Rao
― 5 min read
This study evaluates LLM effectiveness in static and dynamic program slicing tasks.
Kimya Khakzad Shahandashti, Mohammad Mahdi Mohajer, Alvine Boaye Belle
― 6 min read
A detailed look at workload patterns in web applications for improved resource management.
Roozbeh Aghili, Qiaolin Qin, Heng Li
― 7 min read
vMocks streamline formal verification, enhancing software safety and reliability.
Siddharth Priya, Temesghen Kahsai, Arie Gurfinkel
― 6 min read
Bots streamline tasks and improve collaboration in software engineering.
Stefano Lambiase, Gemma Catolino, Fabio Palomba
― 5 min read
A study on how technical debt affects deep learning projects.
Federica Pepe, Fiorella Zampetti, Antonio Mastropaolo
― 6 min read
This article reviews OpenAI's new coding models and their performance in web applications.
Yi Cui
― 5 min read
This study assesses the performance of large code models in API suggestions.
Chaozheng Wang, Shuzheng Gao, Cuiyun Gao
― 6 min read
RepoGenReflex enhances code completion by learning from past experiences and providing relevant suggestions.
Jicheng Wang, Yifeng He, Hao Chen
― 5 min read
This article discusses a new method for generating correctness proofs in Rust.
Chenyuan Yang, Xuheng Li, Md Rakib Hossain Misu
― 5 min read
PromSec optimizes prompts for generating secure and functional code with LLMs.
Mahmoud Nazzal, Issa Khalil, Abdallah Khreishah
― 7 min read
Examining how biases in LLMs affect software team recruitment.
Takashi Nakano, Kazumasa Shimari, Raula Gaikovina Kula
― 5 min read
Research shows how auxiliary functions enhance code generation in instruction-tuned models.
Seonghyeon Lee, Suyeon Kim, Joonwon Jang
― 4 min read
A study examining student challenges and strategies in software modelling tasks.
Shalini Chakraborty, Javier Troya, Lola Burgueño
― 9 min read
A new method enhances software bug detection using LLM agents and a divide-and-conquer strategy.
Md Nakhla Rafi, Dong Jae Kim, Tse-Hsun Chen
― 7 min read
Proxy contracts in Ethereum offer benefits but come with significant security concerns.
Cheng-Kang Chen, Wen-Yi Chu, Muoi Tran
― 7 min read
An automated approach improves log analysis and fault diagnosis in online services.
Junjie Huang, Zhihan Jiang, Jinyang Liu
― 7 min read
Researchers develop methods for better automated data wrangling code through context-rich examples.
Junjie Huang, Daya Guo, Chenglong Wang
― 6 min read
AI tools are changing how developers work and improving the software development process.
Shidong Pan, Litian Wang, Tianyi Zhang
― 6 min read
An overview of the importance and methods for verifying distributed systems.
Lingzhi Ouyang, Xudong Sun, Ruize Tang
― 7 min read
Exploring new methods to improve proof verification in software engineering.
Minghai Lu, Benjamin Delaware, Tianyi Zhang
― 7 min read
Research shows new methods for improving the merging of software code.
Qingyu Zhang, Liangcai Su, Kai Ye
― 5 min read
Exploring Differential GAI’s role in improving code quality for software projects.
Marcus Kessel, Colin Atkinson
― 6 min read
zsLLMCode creates useful code representations efficiently using AI.
Zixiang Xian, Chenhui Cui, Rubing Huang
― 5 min read
Examining firmware vulnerabilities and the tools to enhance security.
Mahsa Farahani, Ghazal Shenavar, Ali Hosseinghorban
― 7 min read
This study assesses how well language models assist beginner programmers with code comments.
Aysa Xuemo Fan, Arun Balajiee Lekshmi Narayanan, Mohammad Hassany
― 4 min read
Examines the impact of protestware on software development and community responses.
Youmei Fan, Dong Wang, Supatsara Wattanakriengkrai
― 6 min read
Using Large Language Models to improve mobile app user feedback analysis.
Tanmai Kumar Ghosh, Atharva Pargaonkar, Nasir U. Eisty
― 9 min read
A new approach enhances code suggestions for software development.
Tuan-Dung Bui, Duc-Thieu Luu-Van, Thanh-Phat Nguyen
― 6 min read
Automating code reviews can enhance developer efficiency and team growth.
Yegor Denisov-Blanch, Igor Ciobanu, Simon Obstbaum
― 7 min read
Enhancing detection methods for harmful packages in software repositories.
Wenbo Guo, Chengwei Liu, Limin Wang
― 6 min read
This framework simplifies understanding of privacy policies using AI technology.
Arda Goknil, Femke B. Gelderblom, Simeon Tverdal
― 8 min read
This article examines problems in LLM projects and suggests solutions for developers.
Yangxiao Cai, Peng Liang, Yifei Wang
― 9 min read
CodeTracker enhances code change tracking by focusing on accuracy and refactoring awareness.
Mohammed Tayeeb Hasan, Nikolaos Tsantalis, Pouria Alikhanifard
― 6 min read
Exploring the importance of accountability in software systems affecting social and legal outcomes.
Saeid Tizpaz-Niari, Shiva Darian, Ashutosh Trivedi
― 5 min read
LLM-Cure streamlines app review analysis for better user experience.
Maram Assi, Safwat Hassan, Ying Zou
― 5 min read
Examining how ChatGPT reshapes responses to programming questions compared to human experts.
Mohammed Mehedi Hasan, Mahady Hasan, Mamun Bin Ibne Reaz
― 7 min read
AI tools like GitHub Copilot boost productivity and satisfaction for developers.
Kevin KB Ng, Liyana Fauzi, Leon Leow
― 7 min read
CodeInsight offers a refined dataset for generating Python code with real examples.
Nathanaël Beau, Benoît Crabbé
― 7 min read