mlsanityData to 7 Oct 2026

SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning

arXiv 2606.08992 ↗First posted 8 Jun 2026cs.RO cs.AI cs.CVcited by 3

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Vision-and-Language Navigation in continuous environments requires agents to understand the spatial structure of previously unseen environments in order to follow language instructions. Although foundation models have opened a promising path toward zero-shot navigation without task-specific policy training, many navigators still rely on local visual cues and linear history-based reasoning, overlooking the spatial nature of navigation across explored regions, traversed paths, landmarks, and their spatial relations. In this paper, we propose SpaceVLN, a navigation agent built around Spatial Cognitive Memory and Task-Guided Spatial Reasoning. Specifically, SpaceVLN introduces an efficient stagewise closed-loop framework where planning and execution are organized around verifiable space--landmark stages. During navigation, the agent progressively abstracts explored regions into Spatial Waypoints and dynamically maintains subtask-grounded landmark evidence, forming a hierarchical Spatial Cognitive Memory for progress localization and spatial-relation understanding. Built on this memory, Spatial-CoT integrates task-progress reasoning with spatial perception, analysis, and prediction, enabling Task-Guided Spatial Reasoning for embodied navigation. The unified stage interface enables SpaceVLN to address both Vision-and-Language Navigation and Object-Goal Navigation under a unified zero-shot setting, without task-specific policy training. Across R2R-CE, RxR-CE, GN-Bench, and HM3D-OVON, SpaceVLN achieves state-of-the-art zero-shot performance, and real-robot deployment further validates its applicability. These results highlight Spatial Cognitive Memory and Task-Guided Spatial Reasoning as a practical foundation for stronger embodied navigation agents.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 56 of its 63 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

56 of 63 references.

Closest ancestors · 5

Same direction, newest first

  1. 2026One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation17 Feb
  2. 2026Kimi K2.5: Visual Agentic Intelligence2 Feb
  3. 2025NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions9 Oct
  4. 2024TANGO: Training-free Embodied AI Agents for Open-world Tasks5 Dec
  5. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents18 Jan

Other references · 51

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  5. 2025Qwen3-VL Technical Reportcited by 2,534
  6. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  7. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  8. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  9. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  10. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  11. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
  12. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
38 more
  1. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 429
  2. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  3. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 401
  4. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 337
  5. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 274
  6. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 268
  7. 2020Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-trainingcited by 228
  8. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  9. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 222
  10. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 201
  11. 2024Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigationcited by 195
  12. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 187
  13. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 165
  14. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 146
  15. 2023Structured Chain-of-Thought Prompting for Code Generationcited by 136
  16. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 127
  17. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 117
  18. 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 111
  19. 2024MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigationcited by 85
  20. 2024NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoningcited by 77
  21. 2024HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigationcited by 71
  22. 2025Embodied Navigation Foundation Modelcited by 65
  23. 2024Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMscited by 60
  24. 2025Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigationcited by 56
  25. 2025MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigationcited by 55
  26. 2023SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environmentscited by 53
  27. 2024Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environmentscited by 49
  28. 2025AI Flow: Perspectives, Scenarios, and Approachescited by 44
  29. 2023RepViT-SAM: Towards Real-Time Segmenting Anythingcited by 17
  30. 2025MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigationcited by 13
  31. 2025FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graphcited by 11
  32. 2025GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigationcited by 10
  33. 2025VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigationcited by 8
  34. 2026SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigationcited by 8
  35. 2026DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigationcited by 5
  36. 2026GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigationcited by 5
  37. 2026Stop Wandering: Efficient Vision-Language Navigation via Metacognitive Reasoningcited by 3
  38. 2026SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipationcited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLNcited by 2
  2. 2026Beyond Spatial Benchmarks: From Spatial Reasoning to Navigationcited by 0
  3. 2026Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wildcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning
  2. 2025From reactive to cognitive: brain-inspired spatial intelligence for embodied agents
  3. 2026HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
  4. 2026Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
  5. 2026HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
  6. 2025Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation
  7. 2026VCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience
  8. 2026AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation