As a codebase expands over time, its library dependencies can become outdated and require updates to maintain innovation and security. However, updating a library can introduce breaking changes in the code, necessitating significant developer time for maintenance. To address this, we introduce a framework of LLM agents to be used in combination with migration documentation to automatically recommend and apply code updates and ensure compatibility with new versions. Our solution can automatically localize updated library usages in live Java codebases and implement recommended fixes in a user-friendly manner. The system architecture consists of multiple key components: a Summary Agent, Control Agent, and Code Agent. To validate our approach, we apply the framework on an industrial use case by which we create three synthetic code repositories with major Upgrade changes and benchmark our approach against state-of-the-art methods. Results show that our approach not only performs upgrades using fewer tokens across all cases but also achieves a precision of 71.4%, highlighting its efficiency and effectiveness compared to state-of-the-art methods.
PCREQ: Automated Inference of Compatible Requirements for Python Third-party Library Upgrades
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Nanjing University（南京大学）；Southern University of Science and Technology（南方科技大学）；Beihang University（北京航空航天大学）
A Data Source Dependency Analysis Framework for Large Scale Data Science Projects
Microsoft（微软）
依赖地狱是大型软件项目开发中众所周知的痛点，机器学习（ML）代码库也不能幸免。事实上，ML应用程序还遭受着另一种形式的依赖地狱，即“数据源依赖地狱”。这个术语指的是数据及其独特的怪癖所扮演的核心角色，这些怪癖通常会导致ML模型的意外失败，而这些失败无法通过代码更改来解释。在本文中，我们提出了一个自动依赖映射框架，允许MLOps工程师在快节奏的工程环境中监视其模型的整个依赖映射，从而提前减轻任何数据源更改的后果（例如，重新训练模型、忽略数据、设置默认数据等）。我们的系统是基于一个统一的和通用的方法，采用静态分析技术，从数据源可以可靠地确定任何类型的依赖范围广泛的源语言和文物。依赖映射框架作为REST Web API公开，其中唯一的输入是托管代码库的Git存储库的路径。目前由微软的MLOps工程师使用，我们预计这种依赖关系映射API将在未来被MLOps工程师更广泛地采用。
Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement
University of the Chinese Academy of Sciences（中国科学院大学）；ByteDance Inc.（字节跳动公司）；Zhejiang University（浙江大学）；National Taiwan University（台湾国立大学）；Peking University（北京大学）；Alibaba Group（阿里巴巴集团）；Tsinghua University（清华大学）；Liaoning Technical University（辽宁技术大学）
LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning
State Key Laboratory of Complex \& Critical Software Environment (SKLCCSE), School of Computer Science；Engineering, Beihang University Beijing China；SKLCCSE, School of Computer Science；School of Computing；Data Science, The University of Hong Kong Hong Kong SAR China；Engineering, Beihang University；Data Science, The University of Hong Kong
