Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMs

Multimodal large language models (MLLMs) are making rapid strides in complex visual reasoning. This survey synthesizes the emerging paradigm of Image-Grounded Chain-of-Thought (IG-CoT), where models ground intermediate inferences by interleaving textual rationales with visual state updates. We formalize IG-CoT, present a method-centric taxonomy covering prompting, supervised finetuning, and reinforcement learning, and map these techniques to representative benchmarks. Our analysis identifies two domains where IG-CoT offers significant advantages: detailoriented reasoning requiring meticulous perception, and imagined-world reasoning for simulating unseen states in games, geometry, and planning. We discuss the practical trade-offs of current methods regarding controllability, data, and compute. We conclude by highlighting key challenges (efficiency, data quality, and generative capabilities) and outlining promising future directions, including lightweight architectures, richer intermediate supervision, and method-aware evaluations that better assess faithfulness and longhorizon reasoning. We maintain a continuously updated paper list at https://github.com/ dddraxxx/Awesome-Image-Grounded-CoT .