Related papers: Evaluating AGENTS.md: Are Repository-Level Context…
The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks…
Context: Given the acknowledged need to understand the people processes enacted during software development, software repositories and mailing lists have become a focus for many studies. However, researchers have tended to use mostly…
Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, repository-level code generation presents unique challenges, particularly due to the need to utilize information spread across…
The rise of large language models (LLMs) has accelerated the development of automated techniques and tools for supporting various software engineering tasks, e.g., program understanding, code generation, software testing, and program…
Large Language Models demonstrate the ability to solve various programming tasks, including code generation. Typically, the performance of LLMs is measured on benchmarks with small or medium-sized context windows of thousands of lines of…
Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…
Large language model (LLM) coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human developers address such issues through refactoring: behavior-preserving program…
Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…
We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them…
LLMs' capabilities are enhanced by using function calls to integrate various data sources or API results into the context window. Typical tools include search, web crawlers, maps, financial data, file systems, and browser usage, etc.…
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often…
Large language model agents have made strong progress on software engineering, yet current systems suffer from a context coupling problem: the standard code editing interface conflates code inspection, modification planning, and edit…
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…
Conversational AI interfaces powered by large language models (LLMs) are increasingly used as coding assistants. However, questions remain about how programmers interact with LLM-based conversational agents, the challenges they encounter,…
The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…
The pervasive use of textual formats in the documentation of software requirements presents a great opportunity for applying large language models (LLMs) to software engineering tasks. High-quality software requirements not only enhance the…
Software developers maintain extensive mental models of code they produce and its context, often relying on memory to retrieve or reconstruct design decisions, edge cases, and debugging experiences. These missing links and data obstruct…
Generative AI plays an increasing role during software engineering activities to make them, e.g., more efficient or provide better quality. However, it is often unclear how much benefit LLMs really provide. We concentrate on software…
This paper introduces SecRepoBench, a benchmark to evaluate code agents on secure code completion in real-world repositories. SecRepoBench has 318 code completion tasks in 27 C/C++ repositories, covering 15 CWEs. We evaluate 29 standalone…