mlsanityData to 7 Oct 2026

LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs

arXiv 2603.16947 ↗First posted 16 Mar 2026cs.CV cs.AIcited by 1

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Although vision-language navigation (VLN) has progressed rapidly, zero-shot VLN in continuous environments (VLN-CE) remains highly challenging when using lightweight vision-language models (VLMs), whose limited reasoning capacity makes long-horizon navigation unreliable. In this paper, we propose LightZeroNav to tackle the three major bottlenecks when using lightweight VLMs in zero-shot VLN-CE,i.e.,information redundancy from multi-source inputs, inaccurate progress estimation caused by noisy textual memory, and task entanglement between action execution and stage transition. Using only RGB observations and a lightweight open-source Qwen3-VL-8B backbone, LightZeroNav achieves competitive performance with GPT-4o (~200B) without task-specific training, graph search, or waypoint predictors, demonstrating its effectiveness in zero-shot VLN-CE.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 19 of its 25 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

19 of 25 references.

References · 19

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  2. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  3. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  4. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  5. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 429
  6. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 150
  7. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 125
  8. 2023GridMM: Grid Memory Map for Vision-and-Language Navigationcited by 117
  9. 2023Discuss Before Moving: Visual Language Navigation via Multi-expert Discussionscited by 108
  10. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  11. 2024MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigationcited by 85
  12. 2024MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notescited by 77
7 more
  1. 2024Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMscited by 60
  2. 2024Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environmentscited by 49
  3. 2025SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigationcited by 29
  4. 2023Safe-VLN: Collision Avoidance for Vision-and-Language Navigation of Autonomous Robots Operating in Continuous Environmentscited by 22
  5. 2025FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Taskscited by 16
  6. 2025DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigationcited by 15
  7. 2025Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Navi-Agent: Unlocalized Monocular Navigation Agentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness
  2. 2026One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints
  3. 2026C2Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation
  4. 2025DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory
  5. 2026SFCo-Nav: Efficient Zero-Shot Visual Language Navigation via Collaboration of Slow LLM and Fast Attributed Graph Alignment
  6. 2025Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation
  7. 2026ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language Models
  8. 2024Balancing Performance and Efficiency in Zero-shot Robotic Navigation