空間樹：多模態大語言模型中空間能力如何分支發展

SpatialTree: How Spatial Abilities Branch Out in MLLMs

December 23, 2025

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

cs.AI

摘要

認知科學研究表明，空間能力呈現從感知到推理再到互動的漸進發展規律。然而在多模態大語言模型（MLLMs）中，這種層級結構仍未被充分理解，現有研究多侷限於狹窄的任務集。我們提出受認知科學啟發的SpatialTree層級框架，將空間能力劃分為四個層級：低階感知（L1）、心理表徵（L2）、模擬推演（L3）和具身協同（L4）。基於此分類體系，我們構建了首個以能力為中心的層級化基準測試，對主流MLLMs在27項子能力上進行全面評估。評估結果揭示出清晰的結構特徵：L1技能基本相互獨立，而高階技能呈現強相關性，表明能力間依賴性隨層級提升而增強。透過定向監督微調實驗，我們發現了有趣的遷移動態——L1層級存在負遷移現象，但從低階到高階能力存在顯著的跨層級正向遷移與協同效應。最後我們探索了全面提升層級能力的方法：發現鼓勵過度「思考」的樸素強化學習（RL）策略不可靠，雖有助複雜推理卻會損害直覺感知。為此我們提出簡潔的自動思考調控機制，抑制不必要的思維鏈長度，使RL能夠穩定提升所有層級的性能。SpatialTree的建立為理解並系統化擴展MLLMs的空間能力提供了概念驗證框架。

English

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.