# Gemini Robotics: Bringing AI into the Physical World arXiv: https://arxiv.org/abs/2503.20020 · HTML: https://mlsanity.com/paper/2503.20020/ ## Key facts - Cited by 83 papers in the map (data through 14 Oct 2026). - Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. - First posted on arXiv 25 Mar 2025. ## Placed in - Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/) ## Built on by (most cited first, 30 of 83) - [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025) - [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026) - [Cambrian-S: Towards Spatial Supersensing in Video](https://mlsanity.com/paper/2511.04670/) (2025) - [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025) - [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026) - [LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies](https://mlsanity.com/paper/2606.15768/) (2026) - [Evaluating Gemini Robotics Policies in a Veo World Simulator](https://mlsanity.com/paper/2512.10675/) (2025) - [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026) - [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026) - [Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces](https://mlsanity.com/paper/2506.00123/) (2025) - [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025) - [ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models](https://mlsanity.com/paper/2601.11404/) (2026) - [dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought](https://mlsanity.com/paper/2509.25681/) (2025) - [RLDX-1 Technical Report](https://mlsanity.com/paper/2605.03269/) (2026) - [Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning](https://mlsanity.com/paper/2510.11027/) (2025) - [Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control](https://mlsanity.com/paper/2602.13193/) (2026) - [EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT](https://mlsanity.com/paper/2510.23569/) (2025) - [SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards](https://mlsanity.com/paper/2511.07403/) (2025) - [Generative AI Act II: Test Time Scaling Drives Cognition Engineering](https://mlsanity.com/paper/2504.13828/) (2025) - [VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents](https://mlsanity.com/paper/2601.16973/) (2026) - [Vero: An Open RL Recipe for General Visual Reasoning](https://mlsanity.com/paper/2604.04917/) (2026) - [Flex-π: A Multi-Stream World-Action Model with Compute Flexibility](https://mlsanity.com/paper/2608.10860/) (2026) - [Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding](https://mlsanity.com/paper/2509.25794/) (2025) - [Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition](https://mlsanity.com/paper/2510.01068/) (2025) - [Mind to Hand: Purposeful Robotic Control via Embodied Reasoning](https://mlsanity.com/paper/2512.08580/) (2025) - [Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision](https://mlsanity.com/paper/2606.30552/) (2026) - [Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training](https://mlsanity.com/paper/2512.24125/) (2025) - [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026) - [NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models](https://mlsanity.com/paper/2605.07794/) (2026) - [PLanAR: Planning-Language-Grounded Agentic Reasoning for Robot Manipulation](https://mlsanity.com/paper/2602.01662/) (2026) ## Abstract (arXiv) Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being robust to variations in object types and positions, handling unseen environments as well as following diverse, open vocabulary instructions. We show that with additional fine-tuning, Gemini Robotics can be specialized to new capabilities including solving long-horizon, highly dexterous tasks, learning new short-horizon tasks from as few as 100 demonstrations and adapting to completely novel robot embodiments. This is made possible because Gemini Robotics builds on top of the Gemini Robotics-ER model, the second model we introduce in this work. Gemini Robotics-ER (Embodied Reasoning) extends Gemini's multimodal reasoning capabilities into the physical world, with enhanced spatial and temporal understanding. This enables capabilities relevant to robotics including object detection, pointing, trajectory and grasp prediction, as well as multi-view correspondence and 3D bounding box predictions. We show how this novel combination can support a variety of robotics applications. We also discuss and address important safety considerations related to this new class of robotics foundation models. The Gemini Robotics family marks a substantial step towards developing general-purpose robots that realizes AI's potential in the physical world.