Code localization is a fundamental challenge in repository-level software engineering tasks such as bug fixing. While existing methods equip language agents with comprehensive tools/interfaces to fetch information from the repository, they overlook the critical aspect of memory, where each instance is typically handled from scratch assuming no prior repository knowledge. In contrast, human developers naturally build long-term repository memory, such as the functionality of key modules and associations between various bug types and their likely fix locations. In this work, we augment language agents with such memory by leveraging a repository's commit history -- a rich yet underutilized resource that chronicles the codebase's evolution. We introduce tools that allow the agent to retrieve from a non-parametric memory encompassing recent historical commits and linked issues, as well as functionality summaries of actively evolving parts of the codebase identified via commit patterns. We demonstrate that augmenting such a memory can significantly improve LocAgent, a state-of-the-art localization framework, on both SWE-bench-verified and the more recent SWE-bench-live benchmarks. Our research contributes towards developing agents that can accumulate and leverage past experience for long-horizon tasks, more closely emulating the expertise of human developers.
Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures
Yildiz Technical University, Dept. of Computer Eng.(Yildiz技术大学,计算机工程系);Yildiz Technical University, Department of Computer Engineering(Yildiz技术大学,计算机工程系)
GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
Institute for Artificial Intelligence, Peking University(人工智能研究院,北京大学);School of Intelligence Science and Technology, Peking University(智能科学与技术学院,北京大学);College of Intelligence Science and Technology, National University of Defense Technology(智能科学与技术学院,国防科技大学)
Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents
Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology(南方科技大学可信自主系统研究院);Southern University of Science and Technology(南方科技大学);Ant Group(蚂蚁集团)
RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair
State Key Laboratory for Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学);Human Language Technology Research Institute, University of Texas at Dallas(人机语言技术研究院,德克萨斯大学达拉斯分校)
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Shanghai Jiao Tong University(上海交通大学);Xinjiang University(新疆大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Independent Researcher(独立研究者);The Chinese University of Hong Kong(香港中文大学)
Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion
Nanjing University(南京大学);State Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室);National Institute of Healthcare Data Science, Nanjing University(南京大学国家卫生数据科学研究院)
CodeMEM: AST-Guided Adaptive Memory for Repository-Level Iterative Code Generation
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机学院);School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院)
CARET: Training-Free Test-Time Scaling for Repository-Level Code Completion
The University of Arizona(亚利桑那大学);California State University, Long Beach(加州州立大学长滩分校);East Carolina University(东卡罗来纳大学);Nankai University(南开大学);Nanyang Technological University, Singapore(新加坡南洋理工大学)
One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
National Key Laboratory for Multimedia Information Processing, Peking University(信息处理国家级重点实验室,北京大学);School of Computer Science, Peking University(北京大学计算机科学学院);Zhongguancun Institute of Artificial Intelligence (ZGCI)(中关村人工智能研究院(ZGCI));Baidu Inc(百度公司)
FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verification
1 State Key Laboratory of Complex \& Critical Software Environment, School of Computer Science;Engineering Beihang University, China;2 School of Software, Beihang University, China;3 Peking University, China