# RoboVQA: Multimodal Long-Horizon Reasoning for Robotics

arXiv: https://arxiv.org/abs/2311.00899 · HTML: https://mlsanity.com/paper/2311.00899/

## Key facts

- Cited by 120 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 3 of its 42 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 3 of 3)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)

## Built on by (most cited first, 30 of 120)

- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action](https://mlsanity.com/paper/2312.17172/) (2023)
- [RT-H: Action Hierarchies Using Language](https://mlsanity.com/paper/2403.01823/) (2024)
- [RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation](https://mlsanity.com/paper/2412.13877/) (2024)
- [Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2406.08085/) (2024)
- [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://mlsanity.com/paper/2503.15558/) (2025)
- [ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning](https://mlsanity.com/paper/2507.16815/) (2025)
- [RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete](https://mlsanity.com/paper/2502.21257/) (2025)
- [RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation](https://mlsanity.com/paper/2406.04339/) (2024)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding](https://mlsanity.com/paper/2501.07888/) (2025)
- [Flash-VStream: Efficient Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2506.23825/) (2025)
- [A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning](https://mlsanity.com/paper/2509.15937/) (2025)
- [ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation](https://mlsanity.com/paper/2409.13682/) (2024)
- [Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method](https://mlsanity.com/paper/2412.09082/) (2024)
- [Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization](https://mlsanity.com/paper/2601.12993/) (2026)
- [Real-World Robot Applications of Foundation Models: A Review](https://mlsanity.com/paper/2402.05741/) (2024)
- [Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2502.07601/) (2025)
- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026)
- [On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)](https://mlsanity.com/paper/2401.02500/) (2024)
- [Towards Generalist Robot Learning from Internet Video: A Survey](https://mlsanity.com/paper/2404.19664/) (2024)
- [VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models](https://mlsanity.com/paper/2601.03309/) (2026)
- [Planning with Reasoning using Vision Language World Model](https://mlsanity.com/paper/2509.02722/) (2025)
- [PAI-Bench: A Comprehensive Benchmark For Physical AI](https://mlsanity.com/paper/2512.01989/) (2025)
- [Generating Robot Constitutions & Benchmarks for Semantic Safety](https://mlsanity.com/paper/2503.08663/) (2025)
- [3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks](https://mlsanity.com/paper/2505.05800/) (2025)
- [EO-1: An Open Unified Embodied Foundation Model for General Robot Control](https://mlsanity.com/paper/2508.21112/) (2025)
- [RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization](https://mlsanity.com/paper/2602.03310/) (2026)

## Abstract (arXiv)

We present a scalable, bottom-up and intrinsically diverse data collection scheme that can be used for high-level reasoning with long and medium horizons and that has 2.2x higher throughput compared to traditional narrow top-down step-by-step collection. We collect realistic data by performing any user requests within the entirety of 3 office buildings and using multiple robot and human embodiments. With this data, we show that models trained on all embodiments perform better than ones trained on the robot data only, even when evaluated solely on robot episodes. We find that for a fixed collection budget it is beneficial to take advantage of cheaper human collection along with robot collection. We release a large and highly diverse (29,520 unique instructions) dataset dubbed RoboVQA containing 829,502 (video, text) pairs for robotics-focused visual question answering. We also demonstrate how evaluating real robot experiments with an intervention mechanism enables performing tasks to completion, making it deployable with human oversight even if imperfect while also providing a single performance metric. We demonstrate a single video-conditioned model named RoboVQA-VideoCoCa trained on our dataset that is capable of performing a variety of grounded high-level reasoning tasks in broad realistic settings with a cognitive intervention rate 46% lower than the zero-shot state of the art visual language model (VLM) baseline and is able to guide real robots through long-horizon tasks. The performance gap with zero-shot state-of-the-art models indicates that a lot of grounded data remains to be collected for real-world deployment, emphasizing the critical need for scalable data collection approaches. Finally, we show that video VLMs significantly outperform single-image VLMs with an average error rate reduction of 19% across all VQA tasks. Data and videos available at https://robovqa.github.io