# AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly

arXiv: https://arxiv.org/abs/2604.08983 · HTML: https://mlsanity.com/paper/2604.08983/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## 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, 23 of 23)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [RoboBrain 2.0 Technical Report](https://mlsanity.com/paper/2507.02029/) (2025)
- [Efficient Part-level 3D Object Generation via Dual Volume Packing](https://mlsanity.com/paper/2506.09980/) (2025)
- [TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2510.07181/) (2025)
- [PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding](https://mlsanity.com/paper/2510.20155/) (2025)
- [REASSEMBLE: A Multimodal Dataset for Contact-rich Robotic Assembly and Disassembly](https://mlsanity.com/paper/2502.05086/) (2025)
- [Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models](https://mlsanity.com/paper/2502.10090/) (2025)
- [HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning](https://mlsanity.com/paper/2507.00833/) (2025)
- [BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly](https://mlsanity.com/paper/2506.06221/) (2025)
- [Manual2Skill++: Connector-Aware General Robotic Assembly from Instruction Manuals via Vision-Language Models](https://mlsanity.com/paper/2510.16344/) (2025)
- [A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation](https://mlsanity.com/paper/2601.11076/) (2026)
- [RealAppliance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manuals](https://mlsanity.com/paper/2512.00287/) (2025)
- [E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework](https://mlsanity.com/paper/2511.21422/) (2025)

## Built on by (most cited first, 2 of 2)

- [Brick-Composer: Using MLLMs for Assembly with Diverse Bricks](https://mlsanity.com/paper/2606.05445/) (2026)
- [AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents](https://mlsanity.com/paper/2609.40353/) (2026)

## Abstract (arXiv)

Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. Recent methods based on vision-language models (VLMs) largely rely on coarse 2D perception and struggle to perform accurate reasoning over complex 3D geometry. To address this limitation, we propose AssemLM, a spatial multimodal large language model for robotic assembly that integrates assembly manuals, point clouds, and textual instructions to predict task-critical 6D assembly poses with explicit geometric understanding. To bridge raw 3D perception and high-level linguistic reasoning, AssemLM employs a specialized point cloud encoder to extract fine-grained geometric and rotational features for accurate 3D spatial reasoning in assembly tasks. In addition, we introduce AssemBench, a large-scale benchmark for assembly-oriented spatial reasoning with over 900K multimodal samples and precise 6D pose annotations, extending evaluation from 2D grounding to full 3D geometric inference. Extensive experiments and real-robot evaluations demonstrate that AssemLM achieves state-of-the-art 6D pose reasoning performance and effectively supports fine-grained, multi-step assembly tasks in real-world settings. Code, models, and the AssemBench dataset will be made publicly available.