mlsanityData to 14 Oct 2026

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions

arXiv 2510.08173 ↗First posted 9 Oct 2025cs.RO cs.AI cs.CLcited by 2

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

Abstract (arXiv)

Instruction-following navigation is a key step toward embodied intelligence. Prior benchmarks mainly focus on semantic understanding but overlook systematically evaluating navigation agents' spatial perception and reasoning capabilities. In this work, we introduce the NavSpace benchmark, which contains six task categories and 1,228 trajectory-instruction pairs designed to probe the spatial intelligence of navigation agents. On this benchmark, we comprehensively evaluate 22 navigation agents, including state-of-the-art navigation models and multimodal large language models. The evaluation results lift the veil on spatial intelligence in embodied navigation. Furthermore, we propose SNav, a new spatially intelligent navigation model. SNav outperforms existing navigation agents on NavSpace and real robot tests, establishing a strong baseline for future work.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 32 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

28 of 32 references.

References · 28

  1. 2025Qwen2.5-VL Technical Reportcited by 5,587
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  4. 2024Qwen2 Technical Reportcited by 2,120
  5. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  6. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 611
  7. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  8. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 466
  9. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  10. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  11. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  12. 2019Vision-and-Dialog Navigationcited by 250
16 more
  1. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 233
  2. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 211
  3. 2024Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigationcited by 196
  4. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  5. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 156
  6. 2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 152
  7. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  8. 2019Stay on the Path: Instruction Fidelity in Vision-and-Language Navigationcited by 130
  9. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 129
  10. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 122
  11. 2025StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modelingcited by 118
  12. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 86
  13. 2025OctoNav: Towards Generalist Embodied Navigationcited by 34
  14. 2025CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Modelcited by 27
  15. 2023Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigationcited by 18
  16. 2024RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environmentscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoningcited by 3
  2. 2026If, Then, Otherwise: Diagnosing Conditional Branching in Vision-Language Navigationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything
  2. 2025From reactive to cognitive: brain-inspired spatial intelligence for embodied agents
  3. 2026Mind over Space: Can Multimodal Large Language Models Mentally Navigate?
  4. 2026HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
  5. 2025Nav-R1: Reasoning and Navigation in Embodied Scenes
  6. 2026Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction
  7. 2026LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
  8. 2026NavHarness: Towards Lifelong Embodied Navigation