Related papers: "Refactoring Runaway": Understanding and Mitigatin…
Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches…
Background. Refactoring is a critical task in software maintenance and is generally performed to enforce the best design and implementation practices or to cope with design defects. Several studies attempted to detect refactoring activities…
Long methods that encapsulate multiple responsibilities within a single method are challenging to maintain. Choosing which statements to extract into new methods has been the target of many research tools. Despite steady improvements, these…
Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space…
We aim to explore how developers document their refactoring activities during the software life cycle. We call such activity Self-Affirmed Refactoring (SAR), which indicates developers' documentation of their refactoring activities. SAR is…
Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation,…
Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests,…
Generating performant executables from high level languages is critical to software performance across a wide range of domains. Modern compilers perform this task by passing code through a series of well-studied optimizations at…
LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal…
Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…
Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program…
Agentic coding systems increasingly use large language models (LLMs) for software engineering tasks such as debugging, root cause analysis, and code review. However, many existing systems encode task logic, execution flow, and output…
With software maintenance accounting for 50% of the cost of developing software, enhancing code quality and reliability has become more critical than ever. In response to this challenge, this doctoral research proposal aims to explore…
Automated code generation has long been considered the holy grail of software engineering. The emergence of Large Language Models (LLMs) has catalyzed a revolutionary breakthrough in this area. However, existing methods that only rely on…
Context. Source code refactoring is a well-established approach to improving source code quality without compromising its external behavior. Motivation. The literature described the benefits of refactoring, yet its application in practice…
Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often…
Redundant code is a persistent challenge in software development that makes systems harder to maintain, scale, and update. It adds unnecessary complexity, hinders bug fixes, and increases technical debt. Despite their impact, removing…
Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain,…
Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains…
Large Language Models (LLMs), such as ChatGPT, have become widely popular and widely used in various software engineering tasks such as refactoring, testing, code review, and program comprehension. Although recent studies have examined the…