Related papers: RepoMirage: Probing Repository Context Reasoning i…

Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Objectives: We study whether temporally stale repository snippets act as harmless noise or…

Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts.…

Maintaining up-to-date, comprehensive documentation for large codebases is a persistent challenge. Recent progress in automated documentation has moved from template-based rules to large language models (LLMs), yet existing tools still…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

Repository-level code completion automatically predicts the unfinished code based on the broader information from the repository. Recent strides in Code Large Language Models (code LLMs) have spurred the development of repository-level code…

Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on…

Language models have been applied to various software development tasks, but the performance varies according to the scale of the models. Large Language Models (LLMs) outperform Small Language Models (SLMs) in complex tasks like…

While Large Language Models (LLMs) have achieved remarkable success in code generation, they often struggle with the deep, long-horizon reasoning required for complex software engineering. We attribute this limitation to the nature of…

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…

Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work, we investigate how…

Issue localization, which identifies faulty code elements such as files or functions, is critical for effective bug fixing. While recent LLM-based and LLM-agent-based approaches improve accuracy, they struggle in large-scale repositories…

Code auditing is the process of reviewing code with the aim of identifying bugs. Large Language Models (LLMs) have demonstrated promising capabilities for this task without requiring compilation, while also supporting user-friendly…

General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system that can handle specific queries about code entities, or code…

Repository aware coding agents often struggle to recover build and test structure, especially in multilingual projects where cross language dependencies are encoded across heterogeneous build systems and tooling. We introduce the Repository…

The evolution of AI coding agents has shifted the frontier from simple snippet completion to autonomous repository-level engineering. However, evaluating these agents remains ill-posed in general code repository generation, where the lack…

We present Code-QA-Bench, a fully automated framework for synthesizing repository-level code understanding benchmarks that separates genuine code comprehension from documentation recall and pretraining memorization. The framework makes two…

Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions,…

Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat each problem in isolation and do not systematically reuse knowledge from prior reasoning…

Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and…

Current repository agents encounter a reasoning disconnect due to fragmented representations, as existing methods rely on isolated API documentation or dependency graphs that lack semantic depth. We consider repository comprehension and…