World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models
Authors: Shouwei Ruan, Bin Wang, Zhenyu Wu, Qihui Zhu, Yuxiang Zhang, Hang Su, Yubin Wang
Organizations: Institute of Artificial Intelligence, Beihang University · Huawei Noah’s Ark Lab · Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center, Tsinghua University
Achieving robust spatial reasoning remains a fundamental challenge for current Multimodal Foundation Models (MFMs). Existing methods either overfit statistical shortcuts via 3D grounding data or remain confined to 2D visual perception, limiting both spatial reasoning accuracy and generalization in unseen scenarios. Inspired by the spatial cognitive mapping mechanisms of biological intelligence, we propose World2Mind, a training-free spatial intelligence toolkit. At its core, World2Mind leverages 3D reconstruction and instance segmentation models to construct structured spatial cognitive maps, empowering MFMs to proactively acquire targeted spatial knowledge regarding interested landmarks and routes of interest. To provide robust geometric-topological priors, World2Mind synthesizes an Allocentric-Spatial Tree (AST) that uses elliptical parameters to model the top-down layout of landmarks accurately. To mitigate the inherent inaccuracies of 3D reconstruction, we introduce a three-stage reasoning chain comprising tool invocation assessment, modality-decoupled cue collection, and geometry-semantics interwoven reasoning. Extensive experiments demonstrate that World2Mind boosts the performance of frontier models, such as GPT-5.2, by 5%~18%. Astonishingly, relying solely on the AST-structured text, purely text-only foundation models can perform complex 3D spatial reasoning, achieving performance approaching that of advanced multimodal models.
Figures & tables
Figure 1: Overview of foundation models performing allocentric spatial reasoning via the proposed World2Mind toolkit. Given egocentric video or multi-view observations, the model first assesses the necessity of tool invocation and subsequently passes key parameters ( e.g . , instances of interest) to World2Mind to drive the generation of spatial cognitive maps. World2Mind integrates an efficient pipeline for 3D reconstruction and semantic-geometry alignment, returning the required structured spatial knowledge through targeted projection and rendering mechanisms. Furthermore, the model conducts geometry-semantics interwoven reasoning based on both the raw visual observations and the geometric cues provided by World2Mind, ultimately yielding highly reliable answers.
Figure 2: Performance comparison under the text-only model (“blind”) setting. we report the performance gap on the VSI-Bench (Tiny subset) between foundation models relying solely on commonsense reasoning and those leveraging world2mind to acquire structured spatial knowledge for allocentric reasoning.
Figure 3: Complete reasoning trace under World2Mind.
Multimodal Foundation Models (MFMs) have made substantial progress, yet remain fragile in spatial reasoning over the physical world. A key bottleneck lies in their inability to transform local egocentric observations into a global allocentric spatial representation. To address this, we propose AlloSpatial, an agentic framework for allocentric spatial cognition in foundation models. AlloSpatial introduces World2Mind, a plug-and-play cognitive mapping sandbox that converts egocentric observations into structured allocentric priors, including Allocentric-Spatial Trees and route maps that support querying object topology, geometric relations, passability, and trajectories. To utilize these priors reliably under noisy reconstruction and ambiguous visual evidence, AlloSpatial introduces a Spatial Reasoning Harness for tool-use judgment, modality-decoupled cue collection, and geometry-semantic arbitration. We further internalize this process in Qwen3-VL through cold-start reinforcement learning with a harness-gated trajectory-level reward. Experiments on VSI-Bench and MindCube show that AlloSpatial improves proprietary models by 5%-18% in a training-free setting, while ASTs alone support strong spatial reasoning even when visual inputs are removed. The trained AlloSpatial agents further outperform larger general-purpose models and competitive spatial baselines, suggesting that structured allocentric representations, active tool use, and verifiable reasoning offer a promising route toward spatially capable foundation models.
Shouwei Ruan, Bin Wang, Zhenyu Wu +5
Institute of Artificial Intelligence, Beihang University · Huawei Noah’s Ark Lab · University of Science and Technology Beijing
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.
Zhenghao Chen, Huiqun Wang, Di Huang
State Key Laboratory of Complex and Critical Software Environment, Beihang University · School of Computer Science and Engineering, Beihang University
Spatial intelligence remains a persistent challenge for Multimodal Large Language Models (MLLMs), as it requires coherent spatial scene representations beyond basic object recognition. Existing methods typically build such representations through textual reasoning or 3D reconstruction. However, they often falter during multi-step reasoning, particularly when required to dynamically re-anchor evidence to the specific camera-, object-, or direction-centric reference frames demanded by complex queries. To address this, we propose OmniView-Space, a framework designed to maintain spatial consistency through multimodal egocentric evidence. Our approach consists of three core components: (1) Multi-Perspective Spatial Mapping (MPSM), which re-anchors reconstructed geometry into a query-aligned visual cognitive map and a textual spatial graph; (2) Tool-Guided Egocentric Reasoning, an interleaved policy trained to actively select the ego anchor required by the query and request the corresponding MPSM evidence; and (3) Cognitive-Map Distillation, which uses MPSM-generated trajectories and ego-frame rewards to train the model to reason with self-generated cognitive maps. Experiments on single- and multi-image spatial reasoning benchmarks show that OmniView-Space achieves state-of-the-art performance. Furthermore, the distilled model maintains this performance while reducing reliance on external geometry pipelines.
Xudong Li, Mengdan Zhang, Peixian Chen +7
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China · Tencent Youtu Lab · Beijing Institute of Technology