{"slug": "scene-graph-thinking-reinforcing-structured-visual-reasoning-for-multimodal", "title": "Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models", "summary": "Researchers introduced Scene Graph Thinking (SaGe), a paradigm that enhances multimodal large language models by converting flat image-text data into structured scene graphs for fine-grained visual reasoning. The method, which includes a data engine and two-stage post-training, achieved significant improvements across eight multimodal benchmarks.", "body_md": "arXiv:2607.05716v1 Announce Type: new\nAbstract: Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image-text corpora into structured scene graphs, where hierarchical entities constitute the nodes and diverse visual relations define the edges. Building upon this, we construct 120K high-quality training data by sampling reasoning traces from scene graphs. Then, two-stage graph-aligned post-training paradigms are introduced, where supervised fine-tuning internalizes MLLMs with structured reasoning, and subsequent reinforcement fine-tuning proposes node-as-proxy graph rewards to consolidate efficient graph exploration. With curated data and graph-aligned training, our approach achieves significant improvements across eight multimodal benchmarks, demonstrating strong effectiveness on fine-grained perception and reasoning tasks. Code is available at https://github.com/zwyang6/SaGe.", "url": "https://wpnews.pro/news/scene-graph-thinking-reinforcing-structured-visual-reasoning-for-multimodal", "canonical_source": "https://arxiv.org/abs/2607.05716", "published_at": "2026-07-08 04:00:00+00:00", "updated_at": "2026-07-08 04:08:58.096930+00:00", "lang": "en", "topics": ["large-language-models", "computer-vision", "natural-language-processing", "ai-research"], "entities": ["Scene Graph Thinking", "SaGe", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/scene-graph-thinking-reinforcing-structured-visual-reasoning-for-multimodal", "markdown": "https://wpnews.pro/news/scene-graph-thinking-reinforcing-structured-visual-reasoning-for-multimodal.md", "text": "https://wpnews.pro/news/scene-graph-thinking-reinforcing-structured-visual-reasoning-for-multimodal.txt", "jsonld": "https://wpnews.pro/news/scene-graph-thinking-reinforcing-structured-visual-reasoning-for-multimodal.jsonld"}}