Preprint
Jul 2026
Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models
This work introduces Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations and proposes node-as-proxy graph rewards to consolidate efficient graph exploration.
Zhiwei Yang, Yuanchen Wu, Nan Zhang et al.
· 1 citation