Related papers: SWE-fficiency: Can Language Models Optimize Real-W…
Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are heterogeneous and persist across interactions. To fill this…
Automatic program repair can be a challenging task, especially when resolving complex issues at a repository-level, which often involves issue reproduction, fault localization, code repair, testing and validation. Issues of this scale can…
With the advancement of automated software engineering, research focus is increasingly shifting toward practical tasks reflecting the day-to-day work of software engineers. Among these tasks, software migration, a critical process of…
The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world…
The rapid advancement of software development practices has introduced challenges in ensuring quality and efficiency across the software engineering (SE) lifecycle. As SE systems grow in complexity, traditional approaches often fail to…
As language agents increasingly automate critical tasks, their ability to follow domain-specific standard operating procedures (SOPs), policies, and constraints when taking actions and making tool calls becomes essential yet remains…
Context: The emergence of Large Language Models (LLMs) has significantly transformed Software Engineering (SE) by providing innovative methods for analyzing software repositories. Objectives: Our objective is to establish a practical…
Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting…
State-of-the-art Large Language Models (LLMs) excel in code generation at the function level. However, the output quality significantly declines when scaling to repository-level systems. Current workflows relying only on natural language…
Large language models (LLMs) and LLM-based Agents have been applied to fix bugs automatically, demonstrating the capability in addressing software defects by engaging in development environment interaction, iterative validation and code…
Large language models (LLMs) have shown strong reasoning and coding capabilities, yet they struggle to generalize to real-world software engineering (SWE) problems that are long-horizon and out of distribution. Existing systems often rely…
Tests can be useful towards resolving issues on code repositories. However, relying too much on tests for issue resolution can lead to code that technically passes observed tests but actually misses important cases or even breaks…
Software security vulnerabilities can lead to severe consequences, making early detection essential. Although code review serves as a critical defense mechanism against security flaws, relevant feedback remains scarce due to limited…
Despite progress in language model (LM) capabilities, evaluations have thus far focused on models' performance on tasks that humans have previously solved, including in programming (Jimenez et al., 2024) and mathematics (Glazer et al.,…
Software engineers operating in complex and dynamic environments must continuously adapt to evolving requirements, learn iteratively from experience, and reconsider their approaches based on new insights. However, current large language…
Repository-level fault localization (FL) and automated program repair (APR) require an agent to identify the relevant code units across files, follow call and data dependencies, and generate a valid patch. Existing graph-based systems…
Researchers have made significant progress in automating the software development process in the past decades. Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use…
Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing benchmarks focus predominantly on single-issue bug fixes…
Code completion has become an essential tool for daily software development. Existing evaluation benchmarks often employ static methods that do not fully capture the dynamic nature of real-world coding environments and face significant…
Data is a cornerstone of empirical software engineering (ESE) research and practice. Data underpin numerous process and project management activities, including the estimation of development effort and the prediction of the likely location…