arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.01929cs.SE
收藏

超越文本仓库探索:面向智能体问题解决的双模态结构推理

Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution

Nanyang Technological University(南洋理工大学);TU Munich(慕尼黑工业大学)

Jiayi Zhang, Kai Huang, Yang Liu, Chunyang Chen

AI总结:

提出DUALVIEW框架,通过模块耦合图、函数调用图、类层次图和程序依赖图四种图视图,结合视觉与文本响应,使智能体在仓库探索中直接推理代码依赖结构,提升长时域问题解决性能。

摘要:

近期在智能体程序修复方面的进展通过迭代仓库探索显著改善了问题解决能力。然而,现有方法主要依赖顺序的、基于文本的代码导航,这从根本上限制了它们对具有复杂长距离依赖的大规模长时域仓库的推理能力。当问题解决智能体通过碎片化的文本观察遍历仓库时,诸如模块组织、调用关系和依赖链等结构信息必须在交互步骤中反复重建,常常导致探索漂移和不完整的定位。我们提出DUALVIEW,一个双模态结构支撑框架,将视觉推理引入问题解决智能体的仓库探索中。DUALVIEW通过四种互补的图视图表示仓库结构:模块耦合图(MCG)、函数调用图(FCG)、类层次图(CHG)和程序依赖图(PDG),并通过可查询的接口以视觉和文本响应形式暴露它们。智能体无需从一系列文本观察中重建仓库结构,而是可以直接对代码依赖的持久视觉表示进行推理,从而实现对长时域代码库的更有效探索和理解。我们在SWE-bench Pro和Verified上评估了DUALVIEW。结果表明,DUALVIEW在不同智能体架构和模型家族中一致地提高了问题解决性能。进一步的消融研究表明,性能提升不仅来自文本结构信息,还来自仓库依赖的视觉外化,这更好地支持了长时域仓库探索。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑