Code generation refers to automatically producing executable programs from user requirements. Recently, researchers have explored approaches to enhance the correctness of generated code with advanced large language models. Although achieving improvements, existing approaches focus on designing reasoning strategies or p...
J. Li, Rui-Qi Bai, Yang Luo et al.· Proceedings of the 41st IEEE...· 0 citations
Despite advances in code retrieval and static analysis, LLM-based coding agents rarely construct or consult structured representations of a codebase's architectural design, domain model, or behavioral patterns, the very knowledge that human developers depend on when making nontrivial changes. This absence of explicit k...
Yi-Ran Zhang, Yi-Fei Ge, Xiao-Xia Liu· Proceedings of the 2nd Inter...· 0 citations
A systematic evaluation of the capability of large language models (LLMs) in new feature implementation, with a task setup strictly aligned with real-world software development practices, shows that new feature implementation of LLMs adhering to real-world world software development practices remains challenges.
J. Li, Ting-Xuan Huang, Tian Zhao et al.· Proceedings of the 41st IEEE...· 0 citations
As software usage continues to expand, package managers automatically resolve dependencies to construct a dependency graph based on user-specified requirements. These explicitly declared dependencies, known as direct dependencies, receive significant attention in terms of maintainability and security. However, implicit...
Lyuye Zhang, Chengwei Liu, Fang-Yuan Zhang et al.· 0 citations
KGMACG is evaluated on three industrial-scale case studies against six state-of-the-art multi-agent baselines: MetaGPT, AutoGen, CAMEL, CrewAI, ChatDev and CodeAgent and indicates that KGMACG advances the automation of application-level software development.
Bo Yang, Xiao Zhang, Wei-Song Sun et al.· ACM Transactions on Software...· 1 citation
SemRef, a framework that combines LLMs with dependency analysis to automatically refine architectures recovered by existing architecture recovery tools, is introduced, which improves accuracy across various metrics and enhances both the accuracy and the comprehension of recovered architectures.
Yi-Ran Zhang, Chengwei Liu, Yu-Qiang Sun et al.· Proceedings of the 2026 IEEE...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.