# STRIVE: Structured Representation Integrating VLM Reasoning for Efficient Object Navigation

arXiv: https://arxiv.org/abs/2505.06729 · HTML: https://mlsanity.com/paper/2505.06729/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 46 references that are in the map.
- First posted on arXiv 10 May 2025.

## 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, 14 of 14)

- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Visual Semantic Navigation using Scene Priors](https://mlsanity.com/paper/1810.06543/) (2018)
- [ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation](https://mlsanity.com/paper/2301.13166/) (2023)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models](https://mlsanity.com/paper/2402.10670/) (2024)
- [An Open and Comprehensive Pipeline for Unified Object Grounding and Detection](https://mlsanity.com/paper/2401.02361/) (2024)
- [Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities](https://mlsanity.com/paper/2410.17385/) (2024)
- [VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model](https://mlsanity.com/paper/2401.02695/) (2024)
- [How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers](https://mlsanity.com/paper/2305.16925/) (2023)
- [3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification](https://mlsanity.com/paper/2212.00338/) (2022)
- [GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering](https://mlsanity.com/paper/2412.14480/) (2024)

## Built on by (most cited first, 5 of 5)

- [3DGSNav: Enhancing Vision-Language Model Reasoning for Object Navigation via Active 3D Gaussian Splatting](https://mlsanity.com/paper/2602.12159/) (2026)
- [Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Views](https://mlsanity.com/paper/2506.03371/) (2025)
- [PIGEON: VLM-Driven Object Navigation via Points of Interest Selection](https://mlsanity.com/paper/2511.13207/) (2025)
- [SR-Nav: Spatial Relationships Matter for Zero-shot Object Goal Navigation](https://mlsanity.com/paper/2603.18443/) (2026)
- [ChronoVision: Temporal Reasoning via Latent State Reconstruction](https://mlsanity.com/paper/2608.05631/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) have been increasingly integrated into object navigation tasks for their rich prior knowledge and strong reasoning abilities. However, applying VLMs to navigation poses two key challenges: effectively representing complex environment information and determining textitwhen and how to query VLMs. Insufficient environment understanding and over-reliance on VLMs (e.g. querying at every step) can lead to unnecessary backtracking and reduced navigation efficiency, especially in continuous environments. To address these challenges, we propose a novel framework that constructs a multi-layer representation of the environment during navigation. This representation consists of viewpoint, object nodes, and room nodes. Viewpoints and object nodes facilitate intra-room exploration and accurate target localization, while room nodes support efficient inter-room planning. Building on this representation, we propose a novel two-stage navigation policy, integrating high-level planning guided by VLM reasoning with low-level VLM-assisted exploration to efficiently locate a goal object. We evaluated our approach on three simulated benchmarks (HM3D, RoboTHOR, and MP3D), and achieved state-of-the-art performance on both the success rate (mathorduparrow, 7.1%) and navigation efficiency (mathorduparrow, 12.5%). We further validate our method on a real robot platform, demonstrating strong robustness across 15 object navigation tasks in 10 different indoor environments. Project page is available at https://zwandering.github.io/STRIVE.github.io/ .