Recent advances in agentic program repair have significantly improved issue resolution by enabling iterative repository exploration. However, existing approaches predominantly rely on sequential, text-based code navigation, which fundamentally limits their ability to reason over large-scale long-horizon repositories with complex and long-range dependencies. As issue-resolution agents traverse repositories through fragmented textual observations, structural information such as module organization, call relationships, and dependency chains must be repeatedly reconstructed across interaction steps, often leading to exploration drift and incomplete localization. We present DUALVIEW, a dual-modal structural scaffolding framework that brings visual reasoning into repository exploration for issue-resolution agents. DUALVIEW represents repository structure through four complementary graph views: Module Coupling Graph (MCG), Function Call Graph (FCG), Class Hierarchy Graph (CHG), and Program Dependence Graph (PDG), and exposes them through a queryable interface with visual and textual responses. Rather than reconstructing repository structure from a sequence of textual observations, agents can directly reason over persistent visual representations of code dependencies, enabling more effective exploration and understanding of long-horizon codebases. We evaluate DUALVIEW on SWE-bench Pro and Verified. Results show that DUALVIEW consistently improves issue-resolution performance across different agent architectures and model families. Further ablation studies demonstrate that the gains arise not only from textual structural information but also from visual externalization of repository dependencies, which better supports long-horizon repository exploration.
CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development
State Key Laboratory of Complex & Critical Software Environment, School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院复杂与关键软件环境国家重点实验室);School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院)
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
University of Waterloo(滑铁卢大学);University of Toronto(多伦多大学);The Hong Kong University of Science and Technology(香港科学与技术大学);McGill University & MILA(麦吉尔大学及MILA);Verdent AI, Inc.(Verdent AI公司)
ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);State Key Laboratory for Novel Software Technology, Nanjing University(南京大学软件新技术国家重点实验室);Singapore Management University(新加坡管理大学)
Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
Singapore Management University(新加坡管理大学);University of Alberta(阿尔伯塔大学);Nanjing University of Science and Technology(南京理工大学);Tel Aviv University(特拉维夫大学)
DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving Repositories
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所人工智能安全重点实验室);University of Chinese Academy of Sciences(中国科学院大学);University of Amsterdam(阿姆斯特丹大学)
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)
ATLAS: Agentic Taxonomy of Large-Scale Software Ecosystems
Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学);Nanyang Technological University(南洋理工大学);Nankai University(南开大学);Sinosoft Company Limited(中软国际有限公司)
Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment
Centre for Software Excellence, Huawei Canada(华为加拿大软件卓越中心);Department of Computer Science, University of Manitoba, Canada(曼尼托巴大学计算机科学系);School of Computing, Queen’s University, Canada(皇后大学计算科学学院)
Where Is the Cost of Third-Party API Routers in Agentic Software Development?
School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);School of Software, Beihang University(北京航空航天大学软件学院);School of Computer Science, Peking University(北京大学计算机科学学院)
研究第三方 API 路由器在代理软件开发中的影响,通过实证研究编码代理中路由器端注入的四个干预级别,开发 SIDEL 框架评估代理,发现路由器端干预难测,客户端缓解措施未完全恢复控制,强调需提供商端输出完整性保证。