# BOP-ASK: Object-Interaction Reasoning for Vision-Language Models

arXiv: https://arxiv.org/abs/2511.16857 · HTML: https://mlsanity.com/paper/2511.16857/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 66 references that are in the map.
- First posted on arXiv 20 Nov 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, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2506.04308/) (2025)
- [SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models](https://mlsanity.com/paper/2412.07755/) (2024)
- [M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place](https://mlsanity.com/paper/2311.00926/) (2023)
- [TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2510.07181/) (2025)
- [ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulation](https://mlsanity.com/paper/2505.09698/) (2025)
- [BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation](https://mlsanity.com/paper/2504.02812/) (2025)
- [Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models](https://mlsanity.com/paper/2308.09778/) (2023)
- [GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation](https://mlsanity.com/paper/2505.13441/) (2025)
- [MapleGrasp: Mask-guided Feature Pooling for Language-driven Efficient Robotic Grasping](https://mlsanity.com/paper/2506.06535/) (2025)

## Built on by (most cited first, 4 of 4)

- [SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL](https://mlsanity.com/paper/2512.04069/) (2025)
- [SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them](https://mlsanity.com/paper/2607.27703/) (2026)
- [PROBE: Manipulation-Grounded Visual Question Answering with VLM Agents](https://mlsanity.com/paper/2608.17129/) (2026)
- [Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena](https://mlsanity.com/paper/2610.00854/) (2026)

## Abstract (arXiv)

Vision Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses in understanding object interactions. Current benchmarks test high level relationships ('left of,' 'behind', etc.) but ignore fine-grained spatial understanding needed for real world applications: precise 3D localization, physical compatibility between objects, object affordances and multi step spatial planning. In this work, we present BOP-ASK, a novel large scale dataset for object interaction reasoning for both training and benchmarking. Our data generation pipeline leverages 6D object poses from the Benchmark for Object Pose Estimation (BOP) datasets from which we derive fine grained annotations such as grasp poses, referred object poses, path planning trajectories, relative spatial and depth relationships, and object-to-object relationships. BOP-ASK comprises over 150k images and 33M question answer pairs spanning six tasks (four novel), providing a rich resource for training and evaluating VLMs. We evaluate proprietary and open sourced VLMs, and conduct human evaluations on BOP-ASK-core, a contributed test benchmark. We also release BOP-ASK-lab, an out-of-distribution benchmark with images not sourced from BOP, enabling testing of generalization. Our experiments demonstrate that models trained on BOP-ASK outperform baselines and exhibit emergent capabilities such as precise object and grasp pose estimation, trajectory planning, and fine-grained object-centric spatial reasoning in cluttered environments.