EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs
For researchers working on spatial reasoning in multimodal LLMs, this work offers a lightweight, geometry-free alternative to 3D-based methods, though improvements are incremental over existing approaches.
EgoMind introduces a Chain-of-Thought framework that uses linguistic reasoning (Role-Play Caption and Progressive Spatial Analysis) to improve spatial cognition in MLLMs without 3D priors, achieving competitive results on four benchmarks with only 5K SFT and 20K RL samples.
Multimodal large language models (MLLMs) are increasingly being applied to spatial cognition tasks, where they are expected to understand and interact with complex environments. Most existing works improve spatial reasoning by introducing 3D priors or geometric supervision, which enhances performance but incurs substantial data preparation and alignment costs. In contrast, purely 2D approaches often struggle with multi-frame spatial reasoning due to their limited ability to capture cross-frame spatial relationships. To address these limitations, we propose EgoMind, a Chain-of-Thought framework that enables geometry-free spatial reasoning through Role-Play Caption, which jointly constructs a coherent linguistic scene graph across frames, and Progressive Spatial Analysis, which progressively reasons toward task-specific questions. With only 5K auto-generated SFT samples and 20K RL samples, EgoMind achieves competitive results on VSI-Bench, SPAR-Bench, SITE-Bench, and SPBench, demonstrating its effectiveness in strengthening the spatial reasoning capabilities of MLLMs and highlighting the potential of linguistic reasoning for spatial cognition. Code and data are released at https://github.com/Hyggge/EgoMind.