VISPATH: Visual-Intent-Guided Path Reasoning for Multimodal Knowledge Graph Question Answering

Researchers proposed VISPATH, a visual-intent-guided path reasoning framework for multimodal knowledge graph question answering (MM-KGQA), according to a new arXiv paper (arXiv:2609.20843v1). VISPATH recomputes hop-specific multimodal intent at each expansion step and prunes candidate paths as complete evidence chains, addressing the tendency of existing MM-KGQA methods to degenerate into text-only graph search after initial entity grounding. With GPT-4o as the backbone, VISPATH surpassed GPT-5.4 on the newly constructed VISPATH-Bench, achieving a 10.6% relative improvement in average accuracy and a 13.1% improvement at 2-hop reasoning.

arXiv:2609.20843v1 Announce Type: new Abstract: Knowledge graph question answering KGQA enables models to answer natural-language questions through structured graph reasoning and has achieved substantial progress across many benchmarks and applications. Recently, multimodal KGQA MM-KGQA has attracted increasing attention because many questions require jointly using multimodal inputs and KG evidence. However, existing MM-KGQA methods typically use multimodal information only for starting entity grounding or evidence retrieval, after which multi-hop reasoning degenerates into text-only graph search. As a result, they cannot exploit multimodal cues that become important at intermediate hops. To address this limitation, we propose VISPATH, a visual-intent-guided path reasoning framework for MM-KGQA. VISPATH first identifies a reliable starting entity by combining multimodal grounding with graph-structural cues. It then performs intent-guided path discovery by recomputing hop-specific multimodal intent from the input, question, and current partial paths, so that each expansion is guided by the current reasoning state. The discovered paths are further refined through reasoning-chain pruning, which evaluates candidate paths as complete evidence chains based on their consistency with the question, reasoning sketch, and hop-specific intent. Finally, VISPATH checks whether the selected evidence is sufficient for answer generation. We further construct VISPATH-Bench, a benchmark for evaluating multimodal multi-hop reasoning over KGs, covering questions that require two to four hops over KG paths. Extensive experiments on VISPATH-Bench and three additional multimodal QA benchmarks show that VISPATH consistently outperforms strong baselines. Notably, with GPT-4o as the backbone, VISPATH surpasses GPT-5.4 on VISPATH-Bench, achieving a 10.6% relative improvement in average accuracy and a 13.1% improvement at 2-hop reasoning.