Spatial Reasoning in Language Models

Latest papers

49 papers12 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

3D Primitives are a Spatial Language for VLMs
May 12, 2026Junze Liu, Kun Qian, Florian Dubost +8Visually Grounded Reasoning 3D Spatial Reasoning
Unity Technologies
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Apr 17, 2026Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian +1Multimodal Model Evaluation Visual Spatial Reasoning
IIT, Hyderabad · Microsoft Research India
Learning to Draw ASCII Improves Spatial Reasoning in Language Models
Apr 16, 2026Shiyuan Huang, Li Liu, Jincheng He +1Representation Learning Spatial Reasoning
University of California, Santa Cruz
Do LLMs Build Spatial World Models? Evidence from Grid-World Maze Tasks
Apr 12, 2026Weijiang Li, Yilin Zhu, Rajarshi Das +1Spatial Reasoning in Language Models LLM World Models
University of Notre Dame · Columbia University · MQube Cognition
Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
Apr 3, 2026Nolan Platt, Sehrish Nizamani, Alp Tural +5Spatial Reasoning in Language Models Multimodal Large Language Models
Virginia Tech, Blacksburg, Virginia, USA · Incoming PhD student, University of Pennsylvania. · University of Virginia, Charlottesville, Virginia, USA
EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs
Apr 1, 2026Zhenghao Chen, Huiqun Wang, Di HuangSpatial Reasoning in Language Models Multimodal Spatial Reasoning
State Key Laboratory of Complex and Critical Software Environment, Beihang University · School of Computer Science and Engineering, Beihang University
STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO
Apr 1, 2026Pukun Zhao, Longxiang Wang, Chen Chen +4Spatial Reasoning in Language Models Spatial Reasoning
Guangdong University of Finance and Economics · Chongqing University · Westlake University +1
Communicating about Space: Language-Mediated Spatial Integration Across Partial Views
Mar 28, 2026Ankur Sikarwar, Debangan Mishra, Sudarshan Nikhil +2Spatial Reasoning in Language Models Spatial Reasoning
Mila – Quebec AI Institute · Université de Montréal · IIIT Hyderabad +1
From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs
Mar 27, 2026Jiyuan An, Liner Yang, Mengyan Wang +3Spatial Reasoning in Language Models Spatial Reasoning
National Language Resources Monitoring and Research Center for Print Media, Beijing Language and Culture University, Beijing, China · School of Information Science, Beijing Language and Culture University, Beijing, China · School of artificial intelligence, Beijing normal university, Beijing, China
CREG: Compass Relational Evidence Graph for Characterizing Directional Structure in VLM Spatial-Reasoning Attribution
Mar 20, 2026Kaizhen Tan, Yang Feng, Heqing DuVLM Evaluation Gradient-Based Attribution
Carnegie Mellon University Pittsburgh, PA, USA · Columbia University New York, NY, USA
Reasoning Gets Harder for LLMs Inside A Dialogue
Mar 20, 2026Ivan Kartáč, Mateusz Lango, Ondřej DušekSpatial Reasoning in Language Models Multi-Turn Dialogue Evaluation
Charles University, Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics Prague, Czechia
Text-to-Stage: Spatial Layouts from Long-form Narratives
Mar 18, 2026Jefferson Hernandez, Swarnadeep Saha, Chenxi Whitehouse +6Spatial Reasoning in Language Models Spatial Reasoning
Rice University · Meta FAIR · Meta Reality Labs Research
Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures
Mar 18, 2026Risham Sidhu, Julia HockenmaierSpatial Reasoning in Language Models Spatial Reasoning
University of Illinois at Urbana-Champaign
Spatial Reasoning is Not a Free Lunch: A Controlled Study on LLaVA
Mar 13, 2026Nahid Alam, Leema Krishna Murali, Siddhant Bharadwaj +7Spatial Reasoning in Language Models Visual Spatial Reasoning
Cohere Labs Community · Eisai Inc. · Indian Institute of Science, Bangalore +4
3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models
Mar 8, 2026Shaoxiong Zhan, Yanlin Lai, Zheng Liu +6Visual Spatial Reasoning Spatial Reasoning in Language Models
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · School of Software Engineering, Chongqing University, Chongqing, China
SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models
Mar 3, 2026Peiyao Jiang, Zequn Qin, Xi LiSpatial Reasoning in Language Models Spatial Reasoning
Zhejiang University · School of Software Technology, Zhejiang University
Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting
Mar 2, 2026Giacomo Frisoni, Lorenzo Molfetta, Mattia Buzzoni +1Spatial Reasoning in Language Models VLM Reasoning
Department of Computer Science and Engineering, University of Bologna
Can Vision-Language Models See Squares? Text-Recognition Mediates Spatial Reasoning Across Three Model Families
Feb 17, 2026Yuval LeventalVision-Language Models VLM Reasoning
Rochester Institute of Technology
SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
Nov 10, 2025Hunar Batra, Haoqin Tu, Hardy Chen +3Multimodal Understanding Scene Graph Generation
University of Oxford · University of California, Santa Cruz

May 12, 2026J/K move · Enter open · S save

3D Primitives are a Spatial Language for VLMs

Junze Liu, Kun Qian, Florian Dubost, Kai Zhong+7

Unity Technologies

Visually Grounded Reasoning 3D Spatial Reasoning Spatial Reasoning Benchmarks CoT Reasoning VLM Reasoning Spatial Reasoning in Language Models+1

Open paper AskPDF arXiv

Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives with correct object counts, classes, and approximate positions, yet the same models fail at simpler spatial questions on the same image. We show that 3D geometric primitives (cubes, spheres, cylinders, expressed in executable code) serve as a powerful intermediate representation for spatial understanding, and exploit this through three contributions. First, we introduce SpatialBabel, a benchmark evaluating fourteen VLMs on primitive-based 3D scene reconstruction across six scene-code languages (programming languages and declarative formats for 3D primitive scenes), revealing that a single model's object-detection F1 can vary by up to

5.7\times

across languages. Second, we propose Code-CoT (Code Chain-of-Thought), a training-free inference strategy that routes spatial reasoning through primitive-based code generation. Code-CoT lifts the SpatialBabel-QA-Score by up to

+6.4

% on primitive scenes and real-photo CV-Bench-3D accuracy by

+5.0

% for VLMs with strong coding capabilities. Third, we propose \textbf{S

^{3}

-FT} (Self-Supervised Spatial Fine-Tuning), which self-supervisedly distills primitive spatial knowledge into general visual reasoning by parsing the model's own Three.js primitive-reconstructions into structured annotations and fine-tuning on the result, with no human labels and no teacher model. Training on primitive images alone, S

^3

-FT improves Qwen3-VL-8B by

+4.6

+8.6

% on SpatialBabel-Primitive-QA,

+9.7

% on CV-Bench-2D, and

+17

% on HallusionBench; the recipe transfers across model families. These results establish geometric primitives in code as both a diagnostic and a transferable spatial vocabulary for VLMs. We will release all artifacts upon publication.