# AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models

arXiv: https://arxiv.org/abs/2605.25901 · HTML: https://mlsanity.com/paper/2605.25901/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 31 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- 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)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding](https://mlsanity.com/paper/2412.00493/) (2024)
- [LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent](https://mlsanity.com/paper/2309.12311/) (2023)
- [SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding](https://mlsanity.com/paper/2401.09340/) (2024)
- [Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance](https://mlsanity.com/paper/2312.10671/) (2023)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2311.15383/) (2023)
- [VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2410.13860/) (2024)
- [ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution](https://mlsanity.com/paper/2303.00246/) (2023)
- [Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding](https://mlsanity.com/paper/2309.04561/) (2023)
- [MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding](https://mlsanity.com/paper/2403.03077/) (2024)
- [Multi-branch Collaborative Learning Network for 3D Visual Grounding](https://mlsanity.com/paper/2407.05363/) (2024)
- [Zero-shot Object Navigation with Vision-Language Models Reasoning](https://mlsanity.com/paper/2410.18570/) (2024)
- [Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking](https://mlsanity.com/paper/2411.16183/) (2024)
- [PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models](https://mlsanity.com/paper/2402.16836/) (2024)
- [Transcrib3D: 3D Referring Expression Resolution through Large Language Models](https://mlsanity.com/paper/2404.19221/) (2024)
- [SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models](https://mlsanity.com/paper/2504.18684/) (2025)
- [IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes](https://mlsanity.com/paper/2503.17406/) (2025)
- [Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems](https://mlsanity.com/paper/2411.14594/) (2024)

## Abstract (arXiv)

3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions. Recent zero-shot methods leverage 2D vision-language models (LVLMs). However, they often rely on existing sets of multi-view images and struggle with the limited semantic and spatial details provided by standard 3D segmentation tools. We present AgentGrounder, a zero-shot 3D visual grounding framework that operates directly on colored point clouds without task-specific 3D training. Our approach follows a two-stage design: (1) an offline stage that applies 3D model to build an Object Lookup Table (OLT) with instance IDs, semantic labels, 3D bounding boxes; and (2) an online tool-driven agent that decomposes each query, retrieves only relevant candidates from the OLT, performs geometric scoring, and triggers image rendering on demand when additional visual evidence (e.g., color, material, or viewpoint-sensitive cues) is required. Compared with fixed anchor-target matching pipelines, this design reduces cascading matching errors and improves context-window efficiency by avoiding prompts overloaded with irrelevant objects. We evaluate on ScanRefer and Nr3D under a zero-shot setting and observe consistent improvements over SeeGround in our setup, including +2.5% Acc@0.5 on ScanRefer and +6.3% on Nr3D, with a notable +6.3% gain on Nr3D view-independent queries. These results show that combining selective retrieval, geometric reasoning, and adaptive visual inspection yields a practical and robust foundation for open-vocabulary 3D grounding. Our code is available at https://github.com/be2rlab/AgentGrounder.