Visual graphs of repository structure added to text inputs for multimodal LLM agents reduce token consumption by up to 26% while maintaining or improving issue-resolution accuracy.
Svrepair: Structured visual reasoning for automated program repair,
3 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.SE 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
DUALVIEW is a dual-modal framework using Module Coupling, Function Call, Class Hierarchy, and Program Dependence graphs to enable persistent structural reasoning for agentic issue resolution, reporting gains on SWE-bench Pro and Verified.
GALA uses hierarchical graph alignment between UI screenshots and code structures to achieve state-of-the-art bug localization in multimodal automated program repair on SWE-bench.
citing papers explorer
-
LLM Agents Can See Code Repositories
Visual graphs of repository structure added to text inputs for multimodal LLM agents reduce token consumption by up to 26% while maintaining or improving issue-resolution accuracy.
-
Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution
DUALVIEW is a dual-modal framework using Module Coupling, Function Call, Class Hierarchy, and Program Dependence graphs to enable persistent structural reasoning for agentic issue resolution, reporting gains on SWE-bench Pro and Verified.
-
GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair
GALA uses hierarchical graph alignment between UI screenshots and code structures to achieve state-of-the-art bug localization in multimodal automated program repair on SWE-bench.