mlsanityData to 14 Oct 2026

Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning

arXiv 2509.00465 ↗First posted 30 Aug 2025cs.RO cs.AI cs.CVcited by 0

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs) and physical embodiment, we present contributions on two fronts: scene representation and spatial reasoning. For perception, we develop robust, scalable, and accurate scene representations using implicit neural models, with contributions in self-supervised camera calibration, high-fidelity depth field generation, and large-scale reconstruction. For spatial reasoning, we enhance the spatial capabilities of LLMs by introducing a novel navigation benchmark, a method for grounding language in 3D, and a state-feedback mechanism to improve long-horizon decision-making. This work lays a foundation for robots that can robustly perceive their surroundings and intelligently act upon complex, language-based commands.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 115 of its 350 references that are in the map. First posted on arXiv 30 Aug 2025.

Builds on

115 of 350 references.

Closest ancestors · 3

Same direction, newest first

  1. 20233D-LLM: Injecting the 3D World into Large Language Models24 Jul
  2. 2023Statler: State-Maintaining Language Models for Embodied Reasoning30 Jun
  3. 2022Inner Monologue: Embodied Reasoning through Planning with Language Models12 Jul

Other references · 112

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  8. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  9. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  10. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  11. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  12. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
38 more
  1. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  6. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  8. 2020Learning to summarize from human feedbackcited by 2,588
  9. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  10. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  11. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  12. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  13. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  14. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,729
  15. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  16. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  17. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  18. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  19. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,095
  20. 2021Measuring Coding Challenge Competence With APPScited by 902
  21. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  22. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  23. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
  24. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 827
  25. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  26. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  27. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
  28. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  29. 2022A Survey on In-context Learningcited by 721
  30. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  31. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 629
  32. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  33. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  34. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  35. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  36. 2021Neural Fields in Visual Computing and Beyondcited by 540
  37. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  38. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 503

50 most cited of 112 All 112 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025REM: Evaluating LLM Embodied Spatial Reasoning through Multi-Frame Trajectories
  2. 2026SpatialPoint: Spatial-aware Point Prediction for Embodied Localization
  3. 2026Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models
  4. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
  5. 2026ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
  6. 2024EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models
  7. 2025SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning
  8. 2025Towards Embodied Cognition in Robots via Spatially Grounded Synthetic Worlds