mlsanityData to 7 Oct 2026

Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer

arXiv 2510.03342 ↗First posted 2 Oct 2025cs.ROcited by 86

Not on the map. Why?

Cited by 35 in Vision-language-action models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the Gemini Robotics model family: Gemini Robotics 1.5, a multi-embodiment Vision-Language-Action (VLA) model, and Gemini Robotics-ER 1.5, a state-of-the-art Embodied Reasoning (ER) model. We are bringing together three major innovations. First, Gemini Robotics 1.5 features a novel architecture and a Motion Transfer (MT) mechanism, which enables it to learn from heterogeneous, multi-embodiment robot data and makes the VLA more general. Second, Gemini Robotics 1.5 interleaves actions with a multi-level internal reasoning process in natural language. This enables the robot to "think before acting" and notably improves its ability to decompose and execute complex, multi-step tasks, and also makes the robot's behavior more interpretable to the user. Third, Gemini Robotics-ER 1.5 establishes a new state-of-the-art for embodied reasoning, i.e., for reasoning capabilities that are critical for robots, such as visual and spatial understanding, task planning, and progress estimation. Together, this family of models takes us a step towards an era of physical agents-enabling robots to perceive, think and then act so they can solve complex multi-step tasks.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 16; 2026: 70.

86 papers.

Sort:

By area:

  1. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  2. 2026Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Groundingcited by 132
  3. 2026A Pragmatic VLA Foundation Modelcited by 97
  4. 2026CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulationcited by 72
  5. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 54
  6. 2025Evaluating Gemini Robotics Policies in a Veo World Simulatorcited by 50
  7. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 45
  8. 2026Code as Agent Harnesscited by 40
  9. 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policiescited by 39
  10. 2025Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulationcited by 37
  11. 2026Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agentscited by 37
  12. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 26
38 more
  1. 2026BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generationcited by 25
  2. 2026Think3D: Thinking with Space for Spatial Reasoningcited by 22
  3. 2025Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoningcited by 21
  4. 2025SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RLcited by 20
  5. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planningcited by 20
  6. 2026A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulationcited by 20
  7. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  8. 2026Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stackcited by 20
  9. 2026Playful Agentic Robot Learningcited by 18
  10. 2025Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policycited by 17
  11. 2026BPP: Long-Context Robot Imitation Learning by Focusing on Key History Framescited by 17
  12. 2026Show-Harness: Just a VLM Agent Can Play Robotscited by 17
  13. 2025DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planningcited by 15
  14. 2025TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videoscited by 13
  15. 2025Towards Spatial Trace with Reasoning in Vision-Language Models for Roboticscited by 12
  16. 2026MolmoPoint: Better Pointing for VLMs with Grounding Tokenscited by 11
  17. 2025Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligencecited by 10
  18. 2026Geometric Action Model for Robot Policy Learningcited by 10
  19. 2026VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracingcited by 9
  20. 2026What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agentscited by 9
  21. 2025Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robotscited by 8
  22. 2026RL-VLA3: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Trainingcited by 7
  23. 2026PLanAR: Planning-Language-Grounded Agentic Reasoning for Robot Manipulationcited by 6
  24. 2026OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policiescited by 6
  25. 2026RoboAgent: Chaining Basic Capabilities for Embodied Task Planningcited by 6
  26. 2026Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Roboticscited by 6
  27. 2026PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Modelscited by 6
  28. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  29. 2026Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervisioncited by 5
  30. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  31. 2026Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Datasetcited by 4
  32. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulationcited by 4
  33. 2025Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimizationcited by 3
  34. 2026Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoningcited by 3
  35. 2026Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Modelscited by 3
  36. 2026ICLR: In-Context Imitation Learning with Visual Reasoningcited by 3
  37. 2026HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Taskcited by 3
  38. 2025R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Spacecited by 2

50 most cited of 86 All 86 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Gemini Robotics: Bringing AI into the Physical World
  2. 2025Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training
  3. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
  4. 2025Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
  5. 2025Mind to Hand: Purposeful Robotic Control via Embodied Reasoning
  6. 2025EO-1: An Open Unified Embodied Foundation Model for General Robot Control
  7. 2026GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture
  8. 2026OneVLA: A Unified Framework for Embodied Tasks