代码大模型 / AI 编程

R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models

Ken Deng, Jiaheng Liu, He Zhu, Congnan Liu, Jingxin Li, Jiakai Wang, Peng Zhao, Chenchen Zhang, Yanan Wu, Xueqiao Yin, Yuanxing Zhang, Zizheng Zhan, Wenbo Su, Bangyu Xiang, Tiezheng Ge, Bo Zheng

机构 * Alibaba Group（阿里巴巴集团） 纠错

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.CL

Developing and Maintaining an Open-Source Repository of AI Evaluations: Challenges and Insights

Alexandra Abbas, Celia Waggoner, Justin Olive

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.CL、cs.AI

AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation

Ali Reza Ibrahimzada, Kaiyao Ke, Mrigank Pawagi, Muhammad Salman Abid, Rangeet Pan, Saurabh Sinha, Reyhaneh Jabbarvand

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Indian Institute of Science（印度科学研究所） ； Cornell University（康奈尔大学） ； IBM Research（IBM研究） 纠错

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.LG

Comments Published in FSE 2025

RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

Jinyao Guo, Chengpeng Wang, Xiangzhe Xu, Zian Su, Xiangyu Zhang

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.PL

Comments 18 pages, 11 tables, 6 figures, 3 listings

Unravelling Technical debt topics through Time, Programming Languages and Repository

Karthik Shivashankar, Antonio Martini

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.LG

DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis

Zeju Li, Changran Xu, Zhengyuan Shi, Zedong Peng, Yi Liu, Yunhao Zhou, Lingfeng Zhou, Chengyu Ma, Jianyuan Zhong, Xi Wang, Jieru Zhao, Zhufei Chu, Xiaoyan Yang, Qiang Xu

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.LG、cs.PL

Comments 8 pages, 3 figures

RAG-Verus: Repository-Level Program Verification with LLMs using Retrieval Augmented Generation

Sicheng Zhong, Jiading Zhu, Yifang Tian, Xujie Si

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.AI

Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs

Nilesh Dhulshette, Sapan Shah, Vinay Kulkarni

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.AI

Comments To appear at LLM4Code@ICSE 2025

GREI Data Repository AI Taxonomy

John Chodacki, Mark Hanhel, Stefano Iacus, Ryan Scherle, Eric Olson, Nici Pfeiffer, Kristi Holmes, Mohammad Hosseini

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.AI、cs.LG

Enhancing Assamese NLP Capabilities: Introducing a Centralized Dataset Repository

S. Tamang, D. J. Bora

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.CL、cs.AI

Comments 6 pages, 1 table, 1 figure

Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repository

Lukas Heiland, Marius Hauser, Justus Bogner

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.AI

Comments Accepted for publication at the International Conference on AI Engineering (CAIN) 2023

NLP-Powered Repository and Search Engine for Academic Papers: A Case Study on Cyber Risk Literature with CyLit

Linfeng Zhang, Changyue Hu, Zhiyu Quan

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.CL、cs.LG

RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion

Huy N. Phan, Hoang N. Phan, Tien N. Nguyen, Nghi D. Q. Bui

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.AI

Unveiling Project-Specific Bias in Neural Code Models

Zhiming Li, Yanzhou Li, Tianlin Li, Mengnan Du, Bozhi Wu, Yushi Cao, Junzhe Jiang, Yang Liu

专题命中 仓库级理解 ：code model(title,abstract)；分类 cs.SE、cs.AI

Comments Accepted by LREC-COLING 2024

REPOFUSE: Repository-Level Code Completion with Fused Dual Context

Ming Liang, Xiaoheng Xie, Gehao Zhang, Xunjin Zheng, Peng Di, wei jiang, Hongwei Chen, Chengpeng Wang, Gang Fan

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.AI

Lessons Learned from Mining the Hugging Face Repository

Joel Castaño, Silverio Martínez-Fernández, Xavier Franch

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.LG

Comments Accepted at the 2024 ACM/IEEE 1st International Workshop on Methodological Issues with Empirical Studies in Software Engineering (WSESE)

Topical: Learning Repository Embeddings from Source Code using Attention

Agathe Lherondelle, Varun Babbar, Yash Satsangi, Fran Silavong, Shaltiel Eloul, Sean Moran

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.AI

Comments Pre-print, under review

PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development

Avirup Sil, Jaydeep Sen, Bhavani Iyer, Martin Franz, Kshitij Fadnis, Mihaela Bornea, Sara Rosenthal, Scott McCarley, Rong Zhang, Vishwajeet Kumar, Yulong Li, Md Arafat Sultan, Riyaz Bhat, Radu Florian, Salim Roukos

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.CL、cs.LG

Repo2Vec: A Comprehensive Embedding Approach for Determining Repository Similarity

Md Omar Faruk Rokon, Pei Yan, Risul Islam, Michalis Faloutsos

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.AI

Comments 10 pages, 8 figures, 5 tables. In press: ICSME'21

Predicting the Number of Reported Bugs in a Software Repository

Hadi Jahanshahi, Mucahit Cevik, Ayşe Başar

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.LG

Journal ref Canadian AI 2020: Advances in Artificial Intelligence pp 309-320

Repository for Reusing Artifacts of Artificial Neural Networks

Javad Ghofrani, Ehsan Kozegar, Mohammad Divband Soorati, Arezoo Bozorgmehr, Hongfei Chen, Maximilian Naake

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE、cs.LG

Comments tool paper https://github.com/ghofrani85/RAN2 7 pages

Meta-repository of screening mammography classifiers

Benjamin Stadnick, Jan Witowski, Vishwaesh Rajiv, Jakub Chłędowski, Farah E. Shamout, Kyunghyun Cho, Krzysztof J. Geras

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.LG

Comments 17 pages, 2 figures. Meta-repository available at https://www.github.com/nyukat/mammography_metarepository ; v3 adds results on the CSAW-CC dataset

EffiHolmes: Differential Profiling-Guided Repository Level Time Inefficiency Fix Localization

EffiHolmes：基于差分分析的仓库级时间低效修复定位

Haowen Yang, Yun Peng, Zishuo Ding

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE

AI总结 EffiHolmes是基于LLM的仓库级时间低效修复定位框架，通过差分分析等技术提升定位精度，在RepoEffi-Bench上优于多种基线方法，且跨模型规模稳健。

Comments Accepted at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026). 13 pages, 3 figures, and 4 tables

Repository-Aware Metamorphic Relation Generation for Augmented Reality Applications using Large Language Models

基于大型语言模型的增强现实应用的仓库感知变形关系生成

Dibyendu Brinto Bose, Jiawei Qin, Chris Brown

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE

AI总结 本文提出一种结合仓库级上下文与推理编排的流水线，利用大型语言模型生成优化的变形关系，在142个移动AR仓库数据集上验证了该方法可构建可靠的领域相关测试预言，能有效检测代码变异。

RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models

RepoReasoner：评估长上下文语言模型的仓库级代码推理能力

Yanlin Wang, Suiquan Wang, Yanli Wang, Bowen Zhang, Daya Guo, Jiachi Chen, Zibin Zheng

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE

AI总结 研究针对现有代码推理基准测试局限，引入RepoReasoner评估仓库级代码推理，通过多阶段管道构建基准，评估输出预测和调用链预测能力，发现当前LLMs在仓库级推理存在局限，为未来相关研究提供方向。

Comments Published in FSE'2026

DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection

DREA：用于仓库级漏洞检测的解耦推理与探索代理

Mingyang Sun, Guozhu Meng

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE

AI总结 研究针对大语言模型用于仓库级漏洞检测时的不足，提出DREA框架，通过规划与探索代理解耦，实现目标导向上下文获取。构建RepoPairBench评估，提升配对正确性，降低成本，还发现安全推理质量是当前大语言模型的瓶颈。

Comments Accepted for presentation at Internetware 2026. 12 pages, 4 figures, and 5 tables

What's Inside a GitHub Repository? An Empirical Study on the Contents of 10K Projects

GitHub仓库中有什么？对10000个项目内容的实证研究

Andre Hora, João Eduardo Montandon, Diego Elias Costa

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE

AI总结 本文通过分析10000个GitHub仓库的文件和目录，揭示了过去十年仓库内容的变化，包括README.md标准化、GitHub Actions兴起、配置格式演变及生成式AI相关内容的增长。

Comments Paper accepted to ICSME 2026

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction

Mastermind: 基于策略学习的仓库级漏洞复现

Mingzhe Du, Luu Anh Tuan, Tianyi Wu, Renyang Liu, Zhijiang Guo, Dong Huang, See-Kiong Ng

机构 * National University of Singapore（新加坡国立大学） ； Nanyang Technological University（南洋理工大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） 纠错

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.AI

AI总结 提出Mastermind双循环框架，通过策略学习（SFT+GRPO）提升LLM代理在仓库级漏洞复现中的表现，在260个训练任务和200个测试任务上达到84.5%通过率，并成功迁移至不同执行器。

RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue

RepoRescue: LLM智能体在全仓库兼容性修复上的实证研究

Zhihao Lin, Mingyi Zhou, Zhensu Sun, Yizhuo Yang, Renyu Yang, David Lo, Li Li

专题命中 仓库级理解 ：repository(title,abstract)；分类 cs.SE

AI总结 研究LLM智能体能否自动修复因环境演化而失效的旧仓库，提出RepoRescue基准，包含315个仓库，评估多种智能体系统，发现跨文件协调是主要难点，且系统间互补性显著。

From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained

从注册表到仓库：AI代理技能如何编写、适配和维护

Haoyu Gao, Jai Lal Lulla, Hong Yi Lin, Sebastian Baltes, Christoph Treude, Mansooreh Zahedi

专题命中 仓库级理解 ：repository(title)；coding agent(abstract)；分类 cs.SE

AI总结 本研究首次对AI代理技能作为工程制品进行实证分析，通过挖掘公共注册表和GitHub仓库中的技能，发现技能重用多为一次性复制，定制化主要适配本地环境，而行为契约几乎不变。