# SpatialTree: How Spatial Abilities Branch Out in MLLMs

Source: [SpatialTree: How Spatial Abilities Branch Out in MLLMs](<https://www.sota2.com/research/paper/694b739d53fdd5c361739bfd>)

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

Data updated: 2026-01-09T05:00:17.290Z

Authors: Yuxi Xiao, Longfei Li, Shen Yan, Xinhang Liu, Sida Peng, Yunchao Wei, Xiaowei Zhou, Bingyi Kang

Published: 2025-12-23T18:59:46.000Z

## Abstract

Cognitive science suggests that spatial ability develops progressively-from perception to reasoning and interaction. Yet in multimodal LLMs (MLLMs), this hierarchy remains poorly understood, as most studies focus on a narrow set of tasks. We introduce SpatialTree, a cognitive-science-inspired hierarchy that organizes spatial abilities into four levels: low-level perception (L1), mental mapping (L2), simulation (L3), and agentic competence (L4). Based on this taxonomy, we construct the first capability-centric hierarchical benchmark, thoroughly evaluating mainstream MLLMs across 27 sub-abilities. The evaluation results reveal a clear structure: L1 skills are largely orthogonal, whereas higher-level skills are strongly correlated, indicating increasing interdependency. Through targeted supervised fine-tuning, we uncover a surprising transfer dynamic-negative transfer within L1, but strong cross-level transfer from low- to high-level abilities with notable synergy. Finally, we explore how to improve the entire hierarchy. We find that naive RL that encourages extensive "thinking" is unreliable: it helps complex reasoning but hurts intuitive perception. We propose a simple auto-think strategy that suppresses unnecessary deliberation, enabling RL to consistently improve performance across all levels. By building SpatialTree, we provide a proof-of-concept framework for understanding and systematically scaling spatial abilities in MLLMs.

## 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.

- [Multimodal Spatial Reasoning on Our-Bench SpatialTree-Bench 1.0 (test)](<https://www.sota2.com/research/sota/multimodal-spatial-reasoning-on-our-bench-spatialtree-bench-1-0-test.md>): Multimodal Spatial Reasoning; Our-Bench SpatialTree-Bench 1.0 (test); Average Score: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.20617>)

[PDF](<https://arxiv.org/pdf/2512.20617.pdf>)
