# Agent3D-Zero: An Agent for Zero-shot 3D Understanding

arXiv: https://arxiv.org/abs/2403.11835 · HTML: https://mlsanity.com/paper/2403.11835/

## Key facts

- Cited by 29 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 34 of its 47 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Deep Modular Co-Attention Networks for Visual Question Answering](https://mlsanity.com/paper/1906.10770/) (2019)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [MultiModal-GPT: A Vision and Language Model for Dialogue with Humans](https://mlsanity.com/paper/2305.04790/) (2023)
- [mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections](https://mlsanity.com/paper/2205.12005/) (2022)
- [Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes](https://mlsanity.com/paper/2308.08769/) (2023)
- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentation](https://mlsanity.com/paper/1904.08963/) (2019)

## Built on by (most cited first, 29 of 29)

- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models](https://mlsanity.com/paper/2412.02193/) (2024)
- [3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer](https://mlsanity.com/paper/2501.01163/) (2025)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2410.13860/) (2024)
- [Visual Prompting in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2409.15310/) (2024)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [Spatial Understanding from Videos: Structured Prompts Meet Simulation Data](https://mlsanity.com/paper/2506.03642/) (2025)
- [Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods](https://mlsanity.com/paper/2511.15722/) (2025)
- [IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering](https://mlsanity.com/paper/2506.23329/) (2025)
- [Space3D-Bench: Spatial 3D Question Answering Benchmark](https://mlsanity.com/paper/2408.16662/) (2024)
- [ROOT: VLM based System for Indoor Scene Understanding and Beyond](https://mlsanity.com/paper/2411.15714/) (2024)
- [TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration](https://mlsanity.com/paper/2410.12183/) (2024)
- [A Review of 3D Object Detection with Vision-Language Models](https://mlsanity.com/paper/2504.18738/) (2025)
- [Warehouse Spatial Question Answering with LLM Agent](https://mlsanity.com/paper/2507.10778/) (2025)
- [GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation](https://mlsanity.com/paper/2510.22118/) (2025)
- [HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering](https://mlsanity.com/paper/2602.15513/) (2026)
- [GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping under Flexible Language Instructions](https://mlsanity.com/paper/2503.16013/) (2025)
- [Zero-Shot 3D Visual Grounding from Vision-Language Models](https://mlsanity.com/paper/2505.22429/) (2025)
- [Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2604.00528/) (2026)
- [TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints](https://mlsanity.com/paper/2508.17595/) (2025)
- [Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy](https://mlsanity.com/paper/2511.11777/) (2025)
- [Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding](https://mlsanity.com/paper/2511.21191/) (2025)
- [Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration](https://mlsanity.com/paper/2605.31196/) (2026)
- [Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation](https://mlsanity.com/paper/2606.03100/) (2026)
- [Agentic Collaborative Cognition for Zero-Shot 3D Understanding](https://mlsanity.com/paper/2606.24649/) (2026)
- [Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering](https://mlsanity.com/paper/2608.18009/) (2026)
- [CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs](https://mlsanity.com/paper/2609.08345/) (2026)
- [CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding](https://mlsanity.com/paper/2609.19911/) (2026)

## Abstract (arXiv)

The ability to understand and reason the 3D real world is a crucial milestone towards artificial general intelligence. The current common practice is to finetune Large Language Models (LLMs) with 3D data and texts to enable 3D understanding. Despite their effectiveness, these approaches are inherently limited by the scale and diversity of the available 3D data. Alternatively, in this work, we introduce Agent3D-Zero, an innovative 3D-aware agent framework addressing the 3D scene understanding in a zero-shot manner. The essence of our approach centers on reconceptualizing the challenge of 3D scene perception as a process of understanding and synthesizing insights from multiple images, inspired by how our human beings attempt to understand 3D scenes. By consolidating this idea, we propose a novel way to make use of a Large Visual Language Model (VLM) via actively selecting and analyzing a series of viewpoints for 3D understanding. Specifically, given an input 3D scene, Agent3D-Zero first processes a bird's-eye view image with custom-designed visual prompts, then iteratively chooses the next viewpoints to observe and summarize the underlying knowledge. A distinctive advantage of Agent3D-Zero is the introduction of novel visual prompts, which significantly unleash the VLMs' ability to identify the most informative viewpoints and thus facilitate observing 3D scenes. Extensive experiments demonstrate the effectiveness of the proposed framework in understanding diverse and previously unseen 3D environments.