# FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graph

arXiv: https://arxiv.org/abs/2509.13733 · HTML: https://mlsanity.com/paper/2509.13733/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2025.

## Built on by (most cited first, 11 of 11)

- [HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering](https://mlsanity.com/paper/2602.15513/) (2026)
- [Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents](https://mlsanity.com/paper/2604.19034/) (2026)
- [SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning](https://mlsanity.com/paper/2606.08992/) (2026)
- [WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models](https://mlsanity.com/paper/2604.07957/) (2026)
- [HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory](https://mlsanity.com/paper/2606.23565/) (2026)
- [Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning](https://mlsanity.com/paper/2601.09111/) (2026)
- [HaltNav: Reactive Visual Halting over Lightweight Topological Priors for Robust Vision-Language Navigation](https://mlsanity.com/paper/2603.12696/) (2026)
- [OpenBelief-Nav: Evidence-Preserving Object Memory for Open-Vocabulary Language-Guided Navigation](https://mlsanity.com/paper/2608.13923/) (2026)
- [CGFM-Nav: Cognitive Graph-Field Memory for Semantic-Guided Lifelong Multimodal Embodied Navigation](https://mlsanity.com/paper/2608.29114/) (2026)
- [Finder: Agentic Closed-Loop Object Finding for Embodied Grounding](https://mlsanity.com/paper/2609.18058/) (2026)
- [Query, Align, and Distill: Navigation-Aware Cross-Modal Interaction for Efficient Vision-and-Language Navigation](https://mlsanity.com/paper/2609.33097/) (2026)

## Abstract (arXiv)

Visual-Language Navigation (VLN) is a fundamental challenge in robotic systems, with broad applications for the deployment of embodied agents in real-world environments. Despite recent advances, existing approaches are limited in long-range spatial reasoning, often exhibiting low success rates and high inference latency, particularly in long-range navigation tasks. To address these limitations, we propose FSR-VLN, a vision-language navigation system that combines a Hierarchical Multi-modal Scene Graph (HMSG) with Fast-to-Slow Navigation Reasoning (FSR). The HMSG provides a multi-modal map representation supporting progressive retrieval, from coarse room-level localization to fine-grained goal view and object identification. Building on HMSG, FSR first performs fast matching to efficiently select candidate rooms, views, and objects, then applies VLM-driven refinement for final goal selection. We evaluated FSR-VLN across four comprehensive indoor datasets collected by humanoid robots, utilizing 87 instructions that encompass a diverse range of object categories. FSR-VLN achieves state-of-the-art (SOTA) performance in all datasets, measured by the retrieval success rate (RSR), while reducing the response time by 82% compared to VLM-based methods on tour videos by activating slow reasoning only when fast intuition fails. Furthermore, we integrate FSR-VLN with speech interaction, planning, and control modules on a Unitree-G1 humanoid robot, enabling natural language interaction and real-time navigation.