mlsanityData to 14 Oct 2026

RoboBrain 2.0 Technical Report

arXiv 2507.02029 ↗First posted 2 Jul 2025cs.ROcited by 89

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two variants: a lightweight 7B model and a full-scale 32B model, featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain 2.0 achieves strong performance across a wide spectrum of embodied reasoning tasks. On both spatial and temporal benchmarks, the 32B variant achieves leading results, surpassing prior open-source and proprietary models. In particular, it supports key real-world embodied AI capabilities, including spatial understanding (e.g., affordance prediction, spatial referring, trajectory forecasting) and temporal decision-making (e.g., closed-loop interaction, multi-agent long-horizon planning, and scene graph updating). This report details the model architecture, data construction, multi-stage training strategies, infrastructure and practical applications. We hope RoboBrain 2.0 advances embodied AI research and serves as a practical step toward building generalist embodied agents. The code, checkpoint and benchmark are available at https://superrobobrain.github.io.

Key facts. Cited by 89 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 2 Jul 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 36; 2026: 53.

89 papers.

Sort:

By area:

  1. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 84
  2. 2025Kwai Keye-VL 1.5 Technical Reportcited by 73
  3. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  4. 2025Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulationcited by 40
  5. 2026VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Modelscited by 39
  6. 2025Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulationcited by 38
  7. 2025TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Roboticscited by 27
  8. 2025Geometrically-Constrained Agent for Spatial Reasoningcited by 26
  9. 2025Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Braincited by 25
  10. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planningcited by 24
  11. 2026Think3D: Thinking with Space for Spatial Reasoningcited by 24
  12. 2025Robix: A Unified Model for Robot Interaction, Reasoning and Planningcited by 23
38 more
  1. 2025Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoningcited by 23
  2. 2025SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RLcited by 21
  3. 2025From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidancecited by 18
  4. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 18
  5. 2025Contrastive Representation Regularization for Vision-Language-Action Modelscited by 17
  6. 2025RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systemscited by 15
  7. 2025Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbolscited by 14
  8. 2025Towards Cross-View Point Correspondence in Vision-Language Modelscited by 14
  9. 2026RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulationcited by 14
  10. 2025Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Taskscited by 13
  11. 2025VisualTrans: A Benchmark for Real-World Visual Transformation Reasoningcited by 12
  12. 2025Towards Spatial Trace with Reasoning in Vision-Language Models for Roboticscited by 12
  13. 2025RynnEC: Bringing MLLMs into Embodied Worldcited by 11
  14. 2025Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigationcited by 10
  15. 2025METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Modelcited by 10
  16. 2026PhyCritic: Multimodal Critic Models for Physical AIcited by 10
  17. 2026LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Modelscited by 10
  18. 2025PhysToolBench: Benchmarking Physical Tool Understanding for MLLMscited by 9
  19. 2025Scaling Up AI-Generated Image Detection with Generator-Aware Prototypescited by 9
  20. 2026ST4VLA: Spatially Guided Training for Vision-Language-Action Modelscited by 9
  21. 2026PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditingcited by 9
  22. 2026Long-Horizon Manipulation via Trace-Conditioned VLA Planningcited by 9
  23. 2025Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosiscited by 8
  24. 2025Mind to Hand: Purposeful Robotic Control via Embodied Reasoningcited by 8
  25. 2026SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Roboticscited by 8
  26. 2025Abstract 3D Perception for Spatial Intelligence in Vision-Language Modelscited by 7
  27. 2026RoboAgent: Chaining Basic Capabilities for Embodied Task Planningcited by 7
  28. 2026FutureNav: Unified World-Action Modeling for Vision-and-Language Navigationcited by 7
  29. 2025MathSticks: A Benchmark for Visual Symbolic Compositional Reasoning with Matchstick Puzzlescited by 5
  30. 2025OmniSAT: Compact Action Token, Faster Auto Regressioncited by 5
  31. 2026Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiationcited by 5
  32. 2026Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulatorscited by 5
  33. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  34. 2026ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AIcited by 5
  35. 2025OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoningcited by 4
  36. 2026Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulationcited by 4
  37. 2026A2Eval: Agentic and Automated Evaluation for Embodied Braincited by 4
  38. 2026See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoningcited by 4

50 most cited of 89 All 89 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026RoboBrain 2.5: Depth in Sight, Time in Mind
  2. 2026Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning
  3. 2026GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture
  4. 2026Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence
  5. 2025Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning
  6. 2026Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models
  7. 2026The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
  8. 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics