# EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs

Source: [EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-27T05:00:21.000Z

Authors: Zhenghao Chen, Huiqun Wang, Di Huang

Published: 2026-04-01T15:28:13.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Spatial Reasoning on SPBench](<https://www.sota2.com/research/sota/spatial-reasoning-on-spbench.md>): Spatial Reasoning; SPBench; SPBench Score: 55.02.

- [Spatial Reasoning on SITE-Bench](<https://www.sota2.com/research/sota/spatial-reasoning-on-site-bench.md>): Spatial Reasoning; SITE-Bench; SITE-Bench Score: 58.03.

- [Spatial Reasoning on SPAR-Bench](<https://www.sota2.com/research/sota/spatial-reasoning-on-spar-bench.md>): Spatial Reasoning; SPAR-Bench; Overall Score: 39.03.

- [Spatial Reasoning on VSI-Bench](<https://www.sota2.com/research/sota/spatial-reasoning-on-vsi-bench.md>): Spatial Reasoning; VSI-Bench; R.Dr.: 47.21.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.03318>)

[PDF](<https://arxiv.org/pdf/2604.03318.pdf>)
