Search papers, labs, and topics across Lattice.
This paper introduces DUALVIEW, a dual-modal structural scaffolding framework that enhances issue-resolution agents' ability to navigate and reason over complex code repositories by integrating visual reasoning with traditional text-based methods. By employing four complementary graph views鈥擬odule Coupling Graph, Function Call Graph, Class Hierarchy Graph, and Program Dependence Graph鈥擠UALVIEW allows agents to directly interact with persistent visual representations of code dependencies, reducing exploration drift and improving localization accuracy. Evaluation on SWE-bench Pro and Verified demonstrates that DUALVIEW significantly outperforms existing approaches across various agent architectures, highlighting the importance of visual externalization in long-horizon code exploration.
Visualizing code dependencies can dramatically enhance issue-resolution performance, outperforming traditional text-based navigation methods.
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.
Tsinghua AI