中文
相关论文

相关论文: RepoMirage: Probing Repository Context Reasoning i…

200 篇论文

As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consistency across massive, real-world, interdependent file systems, has become critical. Current…

软件工程 · 计算机科学 2026-05-05 Jia Li , Yuxin Su , Michael R. Lyu

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can…

软件工程 · 计算机科学 2024-02-26 Ming Liang , Xiaoheng Xie , Gehao Zhang , Xunjin Zheng , Peng Di , wei jiang , Hongwei Chen , Chengpeng Wang , Gang Fan

Recent advancements in code-fluent Large Language Models (LLMs) enabled the research on repository-level code editing. In such tasks, the model navigates and modifies the entire codebase of a project according to request. Hence, such tasks…

软件工程 · 计算机科学 2024-06-10 Alexander Kovrigin , Aleksandra Eliseeva , Yaroslav Zharov , Timofey Bryksin

The escalating complexity of modern codebases has intensified the need for retrieval systems capable of interpreting cross-component change intents, a capability fundamentally absent in conventional function-level search paradigms. While…

软件工程 · 计算机科学 2025-10-30 Aofan Liu , Shiyuan Song , Haoxuan Li , Cehao Yang , Yiyan Qi

Despite the huge success of Large Language Models (LLMs) in coding assistants like GitHub Copilot, these models struggle to understand the context present in the repository (e.g., imports, parent classes, files with similar names, etc.),…

机器学习 · 计算机科学 2023-06-21 Disha Shrivastava , Denis Kocetkov , Harm de Vries , Dzmitry Bahdanau , Torsten Scholak

Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion. However, the invariable use of retrieval in existing methods exposes issues in both efficiency and robustness, with a…

软件工程 · 计算机科学 2024-06-05 Di Wu , Wasi Uddin Ahmad , Dejiao Zhang , Murali Krishna Ramanathan , Xiaofei Ma

The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks typically demand full-fledged code repositories rather than…

软件工程 · 计算机科学 2025-08-26 Huacan Wang , Ziyi Ni , Shuo Zhang , Shuo Lu , Sen Hu , Ziyang He , Chen Hu , Jiaye Lin , Yifu Guo , Ronghao Chen , Xin Li , Daxin Jiang , Yuntao Du , Pin Lyu

Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, existing benchmarks primarily evaluate these agents as black…

软件工程 · 计算机科学 2026-03-30 Shuhan Liu , Zhiyi Zhao , Xing Hu , Kui Liu , Xiaohu Yang , Xin Xia

Repository-level code generation aims to generate code within the context of a specified repository. Existing approaches typically employ retrieval-augmented generation (RAG) techniques to provide LLMs with relevant contextual information…

软件工程 · 计算机科学 2025-11-04 Yang Liu , Li Zhang , Fang Liu , Zhuohang Wang , Donglin Wei , Zhishuo Yang , Kechi Zhang , Jia Li , Lin Shi

The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it is difficult to utilize the useful information scattered in…

计算与语言 · 计算机科学 2023-10-23 Fengji Zhang , Bei Chen , Yue Zhang , Jacky Keung , Jin Liu , Daoguang Zan , Yi Mao , Jian-Guang Lou , Weizhu Chen

Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather…

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…

软件工程 · 计算机科学 2026-03-24 Balaji Dinesh Gangireddi , Aniketh Garikaparthi , Manasi Patwardhan , Arman Cohan

Large Language Models (LLMs) excel in code generation yet struggle with modern AI software engineering tasks. Unlike traditional function-level or file-level coding tasks, AI software engineering requires not only basic coding proficiency…

软件工程 · 计算机科学 2025-03-20 Siru Ouyang , Wenhao Yu , Kaixin Ma , Zilin Xiao , Zhihan Zhang , Mengzhao Jia , Jiawei Han , Hongming Zhang , Dong Yu

Large Language Models (LLMs) have greatly advanced code auto-completion systems, with a potential for substantial productivity enhancements for developers. However, current benchmarks mainly focus on single-file tasks, leaving an assessment…

计算与语言 · 计算机科学 2023-10-05 Tianyang Liu , Canwen Xu , Julian McAuley

With the growing reliance on automated code completion tools in software development, the need for comprehensive evaluation benchmarks has become critical. Existing benchmarks focus more on code completion in function and class level by…

软件工程 · 计算机科学 2025-11-03 Qinyun Wu , Chao Peng , Pengfei Gao , Ruida Hu , Haoyu Gan , Bo Jiang , Jinhe Tang , Zhiwen Deng , Zhanming Guan , Cuiyun Gao , Xia Liu , Ping Yang

Large Language Models (LLMs) have recently emerged as capable coding assistants that operate over large codebases through either agentic exploration or full-context generation. Existing benchmarks capture a broad range of coding…

软件工程 · 计算机科学 2026-03-30 Jiseung Hong , Benjamin G. Ascoli , Jinho D. Choi

Large language models are increasingly used as coding agents for software engineering tasks. Current benchmarks mainly evaluate whether the agent can correctly solve the request or fix the bugs. They largely treat tasks as independent and…

Repository-level code review requires reasoning over project structure, repository context, and file-level implementation details. Existing automated review workflows often collapse these tasks into a single pass, which can reduce…

软件工程 · 计算机科学 2026-03-18 Peng Zhang

Automated program repair (APR) struggles to scale from isolated functions to full repositories, as it demands a global, task-aware understanding to locate necessary changes. Current methods, limited by context and reliant on shallow…

软件工程 · 计算机科学 2026-03-03 Zhongqiang Pan , Chuanyi Li , Wenkang Zhong , Yi Feng , Bin Luo , Vincent Ng

Digital libraries curate millions of research software artefacts yet lack scalable infrastructure for assessing whether those artefacts remain executable. Existing automated assessment tools treat static repository completeness -- what a…

软件工程 · 计算机科学 2026-05-14 Sheeba Samuel , Daniel Mietchen , Jungsan Kim , Waqas Ahmed , Martin Gaedke
‹ 上一页 1 2 3 10 下一页 ›