Spatial Reasoning

Follow this topic Ask about this topic

Spatial reasoning concerns how people and AI systems represent where things are, how they relate, and how those relations change with viewpoint or movement. Common approaches use grids, graphs, coordinate frames, and 3D cognitive maps; others add geometric tools, visual imagination, active viewing, or reinforcement learning with verifiable rewards. Evaluations range from grid mazes and multi-view question answering to egocentric video, simulated navigation and manipulation, and GIS workflows. A central challenge is that success on isolated spatial questions often fails to transfer to consistent world models, perspective transformations, and reliable action over time.

Latest papers

159 papers23 papers in the last four weeks, up 92% on the four weeks before. 0.1% of all new papers.

Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models
Feb 22, 2026Jaeyun Jang, Seunghui Shin, Taeho Park +1Spatial Reasoning Visual Spatial Reasoning
Kyung Hee University, Yongin, Republic of Korea
CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation
Feb 20, 2026Xia Su, Ruiqi Chen, Benlin Liu +4Embodied Spatial Reasoning VLN Benchmarks
University of Washington Seattle, WA, USA · University of California, Santa Cruz Santa Cruz, CA, USA
OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents
Feb 19, 2026Akashah Shabbir, Muhammad Umer Sheikh, Muhammad Akhtar Munir +8Geospatial Reasoning Benchmarks Remote Sensing
Mohamed bin Zayed University of AI, United Arab Emirates · IBM Research, Europe · Linköping University, Sweden +2
Robot Programming with Augmented Reality: The Role of Spatial Ability
Feb 3, 2026Nicolas Leins, Muriel Fischer, Malte Teichmann +2Robotics Human-Robot Interaction
Zuse Institute Berlin, Takustraße 7, 14195 Berlin, Germany · Weizenbaum Institute, Hardenbergstr. 32, 10623 Berlin, Germany · University of Potsdam, Am Neuen Palais 10, 14469 Potsdam, Brandenburg, Germany +1
Resolving Primitive-Sharing Ambiguity in Long-Tailed TLS-Based Industrial MEP Point Cloud Segmentation via Spatial Context Constraints
Jan 27, 2026Chao Yin, Qing Han, Zhiwei Hou +5Class-Imbalanced Learning 3D Point Cloud Segmentation
Guangzhou Institute of Geography, Guangdong Academy of Sciences, Guangzhou, China · School of Geography and Tourism, Hengyang Normal University, Hengyang, China · Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), Guangzhou, China +3
Can MLLMs Find Their Way in a City? Exploring Emergent Navigation from Web-Scale Knowledge
Dec 17, 2025Dwip Dalal, Utkarsh Mishra, Narendra Ahuja +1Visual Navigation Vision-Language Navigation
University of Illinois Urbana-Champaign · Texas A&M University · Microsoft Research, Redmond
MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images
Nov 24, 2025Qirui Wang, Jingyi He, Yining Pan +3Spatial Reasoning Benchmarks Visual Spatial Reasoning
Technical University of Munich, Germany · A*STAR Institute of Advanced Intelligence and Computing, Singapore · Singapore University of Technology and Design, Singapore +1
EgoCogNav: Cognition-aware Human Egocentric Navigation
Nov 15, 2025Zhiwen Qiu, Ziang Liu, Wenqian Niu +2Robot Navigation Egocentric Video Understanding
Cornell University, Ithaca, NY, USA · Georgia Institute of Technology, Atlanta, GA, USA
GeoGR^2:Zero-Shot Geospatial Inference via Geostatistically-Guided Iterative Refinement with LLMs
Aug 6, 2025Jinfan Tang, Kunming Wu, Xieruifeng Gong +4Zero-Shot Learning Geospatial Reasoning
College of Computer Science, Sichuan University · National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University · College of Life Science, Sichuan University

Feb 22, 2026J/K move · Enter open · S save

Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models

Jaeyun Jang, Seunghui Shin, Taeho Park, Hyoseok Hwang

Kyung Hee University, Yongin, Republic of Korea

Spatial Reasoning Visual Spatial Reasoning VLM Reasoning

Open paper AskPDF arXiv

Perspective-aware spatial reasoning involves understanding spatial relationships from specific viewpoints-either egocentric (observer-centered) or allocentric (object-centered). While vision-language models (VLMs) perform well in egocentric settings, their performance deteriorates when reasoning from allocentric viewpoints, where spatial relations must be inferred from the perspective of objects within the scene. In this study, we address this underexplored challenge by introducing Symbolic Projective Layout (SymPL), a framework that reformulates allocentric reasoning into symbolic-layout forms that VLMs inherently handle well. By leveraging four key factors-projection, abstraction, bipartition, and localization-SymPL converts allocentric questions into structured symbolic-layout representations. Extensive experiments demonstrate that this reformulation substantially improves performance in both allocentric and egocentric tasks, enhances robustness under visual illusions and multi-view scenarios, and that each component contributes critically to these gains. These results show that SymPL provides an effective and principled approach for addressing complex perspective-aware spatial reasoning.