SOURCE-LINKED INTELLIGENCE

Visual Graph Reasoning via Knowledge Compilation

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Visual graph reasoning requires answering graph-theoretic questions directly from graph images, where graph topology and state are conveyed visually rather than given in symbolic form. Despite recent progress of vision-language models (VLMs), current approaches to visual graph reasoning still fail on simple visual graph problems. This reveals a fundamental limitation of existing approaches: they prioritize final-answer supervision over the intermediate recovery of an explicit graph representation that preserves graph topology and state from visual input. To address this limitation, we propose

Read original source ↗ Open in workspace

recordType

paper

region

Global