{"slug": "visual-graph-scaffolds-for-structural-reasoning-in-large-language-models", "title": "Visual Graph Scaffolds for Structural Reasoning in Large Language Models", "summary": "Researchers found that visual graph scaffolds significantly improve large language models' multi-hop reasoning compared to flattened text representations of graph structures. In experiments on question-answering tasks, graph-based guidance remained effective even when direct answer hints were removed, while text-based graph guidance degraded reasoning efficiency and answer quality. The findings suggest graphs should be studied not only as external knowledge sources for LLMs but also as visual tools for organizing reasoning processes.", "body_md": "arXiv:2606.02673v1 Announce Type: new\nAbstract: Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time. In this paper, we take a different view: the value of graphs for LLMs lie not only in supplying information, but also in organizing reasoning. Inspired by how humans use graph-structured mind maps to organize branching and converging thoughts, we ask whether graphs can serve as an internal form of reasoning assistance. We study this question on multi-hop question answering tasks, where teacher-provided reasoning traces are rewritten as graph mind maps and used to guide a student model. Our experiments reveal a clear modality gap. When graph structures are flattened into text, their benefits become limited once direct answer hints are removed. Under this abstract guidance setting, both reasoning efficiency and answer quality degrade substantially. In contrast, visual graph guidance remains effective without direct answer clues, and its advantage persists after supervised fine-tuning and KL-based distillation. The above findings support the claim that graphs should be studied not only as external knowledge structures for LLMs, but also as visual scaffolds for organizing reasoning.", "url": "https://wpnews.pro/news/visual-graph-scaffolds-for-structural-reasoning-in-large-language-models", "canonical_source": "https://arxiv.org/abs/2606.02673", "published_at": "2026-06-03 04:00:00+00:00", "updated_at": "2026-06-03 04:16:35.233423+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "artificial-intelligence", "machine-learning", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/visual-graph-scaffolds-for-structural-reasoning-in-large-language-models", "markdown": "https://wpnews.pro/news/visual-graph-scaffolds-for-structural-reasoning-in-large-language-models.md", "text": "https://wpnews.pro/news/visual-graph-scaffolds-for-structural-reasoning-in-large-language-models.txt", "jsonld": "https://wpnews.pro/news/visual-graph-scaffolds-for-structural-reasoning-in-large-language-models.jsonld"}}