mlsanityData to 7 Oct 2026

SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning

arXiv 2501.10074 ↗First posted 17 Jan 2025cs.RO cs.AI cs.CVcited by 62

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks, largely due to their dependence on language-based outputs. While some approaches have introduced a point-based action space to mitigate this issue, they fall short in managing more intricate tasks within complex environments. This deficiency arises from their failure to fully exploit the inherent thinking and reasoning capabilities that are fundamental strengths of Vision-Language Models (VLMs). To address these limitations, we propose a novel approach named SpatialCoT, specifically designed to bolster the spatial reasoning capabilities of VLMs. Our approach comprises two stages: spatial coordinate bi-directional alignment, which aligns vision-language inputs with spatial coordinates, and chain-of-thought spatial grounding, which harnesses the reasoning capabilities of language models for advanced spatial reasoning. We evaluate SpatialCoT on challenging navigation and manipulation tasks, both in simulation and real-world settings. Experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches in both tasks.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 31 of its 35 references that are in the map. First posted on arXiv 17 Jan 2025.

Builds on

31 of 35 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces18 Dec
  2. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul
  3. 2024GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs19 Jun
  4. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models3 Jun
  5. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities22 Jan
  6. 2022Inner Monologue: Embodied Reasoning through Planning with Language Models12 Jul

Other references · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  7. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  8. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  9. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  10. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  11. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  12. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
13 more
  1. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  2. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  3. 2023A Comprehensive Overview of Large Language Modelscited by 639
  4. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 610
  5. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  6. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  7. 2019CLEVRER: CoLlision Events for Video REpresentation and Reasoningcited by 475
  8. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 277
  9. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Roboticscited by 242
  10. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  11. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  12. 2023Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisitioncited by 156
  13. 2024RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Roboticscited by 133

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 38; 2026: 24.

62 papers.

Sort:

By area:

  1. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  2. 2025What Can RL Bring to VLA Generalization? An Empirical Studycited by 102
  3. 2025Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Viewscited by 58
  4. 2025Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulationcited by 41
  5. 2025VisRL: Intention-Driven Visual Perception via Reinforced Reasoningcited by 39
  6. 2025Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulationcited by 36
  7. 20253D Aware Region Prompted Vision Language Modelcited by 31
  8. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 31
  9. 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMscited by 30
  10. 2025Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecturecited by 30
  11. 2025Spatial Understanding from Videos: Structured Prompts Meet Simulation Datacited by 28
  12. 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoningcited by 27
38 more
  1. 2025SIFThinker: Spatially-Aware Image Focus for Visual Reasoningcited by 25
  2. 2025Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipescited by 22
  3. 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methodscited by 22
  4. 2025ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videoscited by 21
  5. 2025SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RLcited by 20
  6. 2026ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loopcited by 19
  7. 2025SpaceVista: All-Scale Visual Spatial Reasoning from mm to kmcited by 18
  8. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 17
  9. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 14
  10. 2025ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Modelscited by 13
  11. 2025Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMscited by 12
  12. 2025Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learningcited by 9
  13. 2025COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligencecited by 9
  14. 2025Free-form language-based robotic reasoning and graspingcited by 8
  15. 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
  16. 2025SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenescited by 7
  17. 2025Understanding Dynamic Scenes in Ego Centric 4D Point Cloudscited by 6
  18. 2026SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Taskscited by 6
  19. 2025EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoningcited by 4
  20. 2025LRR-Bench: Left, Right or Rotate? Vision-Language models Still Struggle With Spatial Understanding Taskscited by 4
  21. 20263ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Modelscited by 4
  22. 2025Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neurosciencecited by 3
  23. 2025MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agentscited by 3
  24. 2025Scaling Spatial Reasoning in MLLMs through Programmatic Data Synthesiscited by 3
  25. 20263D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editingcited by 3
  26. 2026World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoningcited by 3
  27. 20264DThinker: Thinking with 4D Imagery for Dynamic Spatial Understandingcited by 3
  28. 2025Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoningcited by 2
  29. 2026Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimationcited by 2
  30. 2026Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignmentcited by 2
  31. 2026DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Drivingcited by 2
  32. 2025AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoningcited by 1
  33. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  34. 2026Grounded 3D-Aware Spatial Vision-Language Modelingcited by 1
  35. 2026OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mappingcited by 1
  36. 2026SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Videocited by 1
  37. 2026ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?cited by 1
  38. 2025Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Modelscited by 0

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
  2. 2025Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models
  3. 2026Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models
  4. 2025EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
  5. 2025Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning
  6. 2026MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation
  7. 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
  8. 2025REM: Evaluating LLM Embodied Spatial Reasoning through Multi-Frame Trajectories