# GoalVLM: VLM-driven Object Goal Navigation for Multi-Agent System

arXiv: https://arxiv.org/abs/2603.18210 · HTML: https://mlsanity.com/paper/2603.18210/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 12 of 12)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [L3MVN: Leveraging Large Language Models for Visual Target Navigation](https://mlsanity.com/paper/2304.05501/) (2023)
- [GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation](https://mlsanity.com/paper/2404.06609/) (2024)
- [HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation](https://mlsanity.com/paper/2409.14296/) (2024)
- [ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion](https://mlsanity.com/paper/2504.14478/) (2025)
- [Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration](https://mlsanity.com/paper/2412.18292/) (2024)
- [DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory](https://mlsanity.com/paper/2506.15096/) (2025)

## Built on by (most cited first, 1 of 1)

- [VTM-Nav: Harnessing Cross-Episode Experience for Object-Goal Navigation with Hierarchical Visual-Topological Memory](https://mlsanity.com/paper/2607.14514/) (2026)

## Abstract (arXiv)

Object-goal navigation has traditionally been limited to ground robots with closed-set object vocabularies. Existing multi-agent approaches depend on precomputed probabilistic graphs tied to fixed category sets, precluding generalization to novel goals at test time. We present GoalVLM, a cooperative multi-agent framework for zero-shot, open-vocabulary object navigation. GoalVLM integrates a Vision-Language Model (VLM) directly into the decision loop, SAM3 for text-prompted detection and segmentation, and SpaceOM for spatial reasoning, enabling agents to interpret free-form language goals and score frontiers via zero-shot semantic priors without retraining. Each agent builds a BEV semantic map from depth-projected voxel splatting, while a Goal Projector back-projects detections through calibrated depth into the map for reliable goal localization. A constraint-guided reasoning layer evaluates frontiers through a structured prompt chain (scene captioning, room-type classification, perception gating, multi-frontier ranking), injecting commonsense priors into exploration. We evaluate GoalVLM on GOAT-Bench val_unseen (360 multi-subtask episodes, 1032 sequential object-goal subtasks, HM3D scenes), where each episode requires navigating to a chain of 5-7 open-vocabulary targets. GoalVLM with N=2 agents achieves 55.8% subtask SR and 18.3% SPL, competitive with state-of-the-art methods while requiring no task-specific training. Ablation studies confirm the contributions of VLM-guided frontier reasoning and depth-projected goal localization.