# End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering

arXiv: https://arxiv.org/abs/2411.05755 · HTML: https://mlsanity.com/paper/2411.05755/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 8 Nov 2024.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects](https://mlsanity.com/paper/2006.13171/) (2020)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [Vision language models are blind: Failing to translate detailed visual features into words](https://mlsanity.com/paper/2407.06581/) (2024)
- [GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation](https://mlsanity.com/paper/2311.07562/) (2023)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [Habitat-Matterport 3D Semantics Dataset](https://mlsanity.com/paper/2210.05633/) (2022)
- [GOAT: GO to Any Thing](https://mlsanity.com/paper/2311.06430/) (2023)
- [Explore until Confident: Efficient Exploration for Embodied Question Answering](https://mlsanity.com/paper/2403.15941/) (2024)
- [OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models](https://mlsanity.com/paper/2402.10670/) (2024)
- [Does Spatial Cognition Emerge in Frontier Models?](https://mlsanity.com/paper/2410.06468/) (2024)
- [VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks](https://mlsanity.com/paper/2401.13649/) (2024)
- [CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments](https://mlsanity.com/paper/2403.15637/) (2024)
- [Frontier Based Exploration for Autonomous Robot](https://mlsanity.com/paper/1806.03581/) (2018)

## Built on by (most cited first, 30 of 37)

- [WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation](https://mlsanity.com/paper/2503.02247/) (2025)
- [Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning](https://mlsanity.com/paper/2510.27606/) (2025)
- [Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation](https://mlsanity.com/paper/2502.14254/) (2025)
- [Can Large Vision Language Models Read Maps Like a Human?](https://mlsanity.com/paper/2503.14607/) (2025)
- [MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation](https://mlsanity.com/paper/2511.10376/) (2025)
- [NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks](https://mlsanity.com/paper/2508.02046/) (2025)
- [WoMAP: World Models For Embodied Open-Vocabulary Object Localization](https://mlsanity.com/paper/2506.01600/) (2025)
- [CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?](https://mlsanity.com/paper/2512.16755/) (2025)
- [CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking](https://mlsanity.com/paper/2507.11334/) (2025)
- [DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation](https://mlsanity.com/paper/2505.21969/) (2025)
- [CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation](https://mlsanity.com/paper/2602.18424/) (2026)
- [Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration](https://mlsanity.com/paper/2512.02458/) (2025)
- [Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation](https://mlsanity.com/paper/2602.05789/) (2026)
- [GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning](https://mlsanity.com/paper/2603.19137/) (2026)
- [The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models](https://mlsanity.com/paper/2603.22278/) (2026)
- [Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies](https://mlsanity.com/paper/2412.02125/) (2024)
- [Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience](https://mlsanity.com/paper/2505.05515/) (2025)
- [SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization](https://mlsanity.com/paper/2512.02631/) (2025)
- [OpenFrontier: General Navigation with Visual-Language Grounded Frontiers](https://mlsanity.com/paper/2603.05377/) (2026)
- [Structured Observation Language for Efficient and Generalizable Vision-Language Navigation](https://mlsanity.com/paper/2603.27577/) (2026)
- [GUI Agents with Reinforcement Learning: Toward Digital Inhabitants](https://mlsanity.com/paper/2604.27955/) (2026)
- [SoraNav: Adaptive UAV Task-Centric Navigation via Zeroshot VLM Reasoning](https://mlsanity.com/paper/2510.25191/) (2025)
- [LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating](https://mlsanity.com/paper/2512.09920/) (2025)
- [MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation](https://mlsanity.com/paper/2602.05467/) (2026)
- [CoFL: Continuous Flow Fields for Language-Conditioned Navigation](https://mlsanity.com/paper/2603.02854/) (2026)
- [ReMemNav: Memory-Based Decision Correction and Target Verification for Zero-Shot Object Navigation](https://mlsanity.com/paper/2603.26788/) (2026)
- [WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models](https://mlsanity.com/paper/2604.07957/) (2026)
- [Visually-grounded Humanoid Agents](https://mlsanity.com/paper/2604.08509/) (2026)
- [LIME: Learning Intent-aware Camera Motion from Egocentric Video](https://mlsanity.com/paper/2607.02417/) (2026)
- [ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination](https://mlsanity.com/paper/2512.17435/) (2025)

## Abstract (arXiv)

We present VLMnav, an embodied framework to transform a Vision-Language Model (VLM) into an end-to-end navigation policy. In contrast to prior work, we do not rely on a separation between perception, planning, and control; instead, we use a VLM to directly select actions in one step. Surprisingly, we find that a VLM can be used as an end-to-end policy zero-shot, i.e., without any fine-tuning or exposure to navigation data. This makes our approach open-ended and generalizable to any downstream navigation task. We run an extensive study to evaluate the performance of our approach in comparison to baseline prompting methods. In addition, we perform a design analysis to understand the most impactful design decisions. Visual examples and code for our project can be found at https://jirl-upenn.github.io/VLMnav/