mlsanityData to 7 Oct 2026

ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation

arXiv 2603.08007 ↗First posted 9 Mar 2026cs.CV cs.AIcited by 2

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Existing aerial Vision-Language Navigation (VLN) methods predominantly adopt a detection-and-planning pipeline, which converts open-vocabulary detections into discrete textual scene graphs. These approaches are plagued by inadequate spatial reasoning capabilities and inherent linguistic ambiguities. To address these bottlenecks, we propose a Visual-Spatial Reasoning (ViSA) enhanced framework for aerial VLN. Specifically, a triple-phase collaborative architecture is designed to leverage structured visual prompting, enabling Vision-Language Models (VLMs) to perform direct reasoning on image planes without the need for additional training or complex intermediate representations. Comprehensive evaluations on the CityNav benchmark demonstrate that the ViSA-enhanced VLN achieves a 70.3% improvement in success rate compared to the fully trained state-of-the-art (SOTA) method, elucidating its great potential as a backbone for aerial VLN systems.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 31 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

20 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory8 May
  2. 2025GeoNav: Empowering MLLMs with dual-scale geospatial reasoning for language-goal aerial navigation13 Apr
  3. 2024Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation11 Oct

Other references · 17

  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2023Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4Vcited by 291
  3. 2024Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Wantcited by 98
  4. 2024Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodologycited by 92
  5. 2024Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Modelscited by 79
  6. 2024Visual Prompting in Multimodal Large Language Models: A Surveycited by 52
  7. 2024CityNav: A Large-Scale Dataset for Real-World Aerial Navigationcited by 40
  8. 2024Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Modelscited by 27
  9. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  10. 2025FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Modelscited by 22
  11. 2024Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Modelscited by 16
  12. 2023CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Datacited by 15
5 more
  1. 2024Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Promptscited by 9
  2. 2025SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Modelscited by 9
  3. 2026Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflictscited by 7
  4. 2026The Spatial Blindspot of Vision-Language Modelscited by 5
  5. 2025VPN: Visual Prompt Navigationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigationcited by 2
  2. 2026Structured World-State Reasoning for Agentic Robotic Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning
  2. 2026Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models
  3. 2026Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation
  4. 2025UAV-VLN: End-to-End Vision Language guided Navigation for UAVs
  5. 2026LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation
  6. 2026Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory
  7. 2026Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
  8. 2026Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation