相关论文: Operation-based Refactoring-aware Merging: An Empi…

The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks. However, existing RAG paradigms often overlook the cognitive…

Semantic conflicts arise when a developer introduces changes to a codebase that unintentionally affect the behavior of changes integrated in parallel by other developers. Traditional merge tools are unable to detect such conflicts, so…

With distributed computing and mobile applications becoming ever more prevalent, synchronizing diverging replicas of the same data is a common problem. Reconciliation -- bringing two replicas of the same data structure as close as possible…

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

Collaborative working is increasingly popular, but it presents challenges due to the need for high responsiveness and disconnected work support. To address these challenges the data is optimistically replicated at the edges of the network,…

Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts,…

Performance is a critical quality attribute in software development, yet the impact of method-level code changes on performance evolution remains poorly understood. While developers often make intuitive assumptions about which types of…

Game level editing is the process of constructing a full game level starting from 3D asset libraries, e.g. 3d models, textures, shaders, scripts. In level editing, designers define the look and behavior of the whole level by placing…

Retrieval-Augmented Generation (RAG) systems typically face constraints because of their inherent mechanism: a simple top-k semantic search [1]. The approach often leads to the incorporation of irrelevant or redundant information in the…

Context: The increasing reliance on Code Generation Tools (CGTs), such as Windsurf and GitHub Copilot, are revamping programming workflows and raising critical questions about fairness and inclusivity. While CGTs offer potential…

Large language models (LLMs) equipped with retrieval--the Retrieval-Augmented Generation (RAG) paradigm--should combine their parametric knowledge with external evidence, yet in practice they often hallucinate, over-trust noisy snippets, or…

Optimization modeling underpins decision-making in logistics, manufacturing, energy, and finance, yet translating natural-language requirements into correct optimization formulations and solver-executable code remains labor-intensive.…

Context: Software refactoring aims to improve software quality and developer productivity. Numerous empirical studies investigating the impact of refactoring activities on software quality have been conducted over the last two decades.…

Architectural smells such as God Class, Cyclic Dependency, and Hub-like Dependency degrade software quality and maintainability. Existing tools detect such smells but rarely suggest how to fix them. This paper explores the use of…

A source code difference (diff) indicates changes made by comparing new and old source codes, and it can be utilized in code reviews to help developers understand the changes made to the code. Although many diff generation methods have been…

Software vulnerabilities often persist or re-emerge even after being fixed, revealing the complex interplay between code evolution and socio-technical factors. While source code metrics provide useful indicators of vulnerabilities, software…

Researchers and practitioners have designed and implemented various automated test case generators to support effective software testing. Such generators exist for various languages (e.g., Java, C#, or Python) and for various platforms…

The migration process between different third-party libraries is hard, complex and error-prone. Typically, during a library migration, developers need to find methods in the new library that are most adequate in replacing the old methods of…

Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph…

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…