mlsanityData to 14 Oct 2026

Vision Language Action Models in Robotic Manipulation: A Systematic Review

arXiv 2507.10672 ↗First posted 14 Jul 2025cs.RO cs.CVcited by 38

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Vision Language Action (VLA) models represent a transformative shift in robotics, with the aim of unifying visual perception, natural language understanding, and embodied control within a single learning framework. This review presents a comprehensive and forward-looking synthesis of the VLA paradigm, with a particular emphasis on robotic manipulation and instruction-driven autonomy. We comprehensively analyze 102 VLA models, 26 foundational datasets, and 12 simulation platforms that collectively shape the development and evaluation of VLAs models. These models are categorized into key architectural paradigms, each reflecting distinct strategies for integrating vision, language, and control in robotic systems. Foundational datasets are evaluated using a novel criterion based on task complexity, variety of modalities, and dataset scale, allowing a comparative analysis of their suitability for generalist policy learning. We introduce a two-dimensional characterization framework that organizes these datasets based on semantic richness and multimodal alignment, showing underexplored regions in the current data landscape. Simulation environments are evaluated for their effectiveness in generating large-scale data, as well as their ability to facilitate transfer from simulation to real-world settings and the variety of supported tasks. Using both academic and industrial contributions, we recognize ongoing challenges and outline strategic directions such as scalable pretraining protocols, modular architectural design, and robust multimodal alignment strategies. This review serves as both a technical reference and a conceptual roadmap for advancing embodiment and robotic control, providing insights that span from dataset generation to real world deployment of generalist robotic agents.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 96 of its 156 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

96 of 156 references.

Closest ancestors · 19

Same direction, newest first

  1. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  2. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better29 May
  3. 2025Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions16 May
  4. 2025Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions4 May
  5. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  6. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  7. 2025VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation19 Feb
  8. 2025GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation13 Feb
  9. 2025HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation8 Feb
  10. 2025Scalable, Training-Free Visual Language Robotics: A Modular Multi-Model Framework for Consumer-Grade GPUs3 Feb
  11. 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent31 Jan
  12. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks9 Dec
7 more
  1. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigation5 Dec
  2. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation29 Nov
  3. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks4 Nov
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  5. 2024LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulation7 Oct
  6. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers12 Sep
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 77

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  8. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  9. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  10. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  11. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  12. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
38 more
  1. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  2. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  3. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  4. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  5. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
  6. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 788
  7. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  8. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
  9. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  10. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  11. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  12. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  13. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  14. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  15. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 407
  16. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 405
  17. 2017Embodied Question Answeringcited by 336
  18. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 304
  19. 2016Using the Output Embedding to Improve Language Modelscited by 272
  20. 2018Unity: A General Platform for Intelligent Agentscited by 236
  21. 2024ShowUI: One Vision-Language-Action Model for GUI Visual Agentcited by 232
  22. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 221
  23. 2021TEACh: Task-driven Embodied Agents that Chatcited by 197
  24. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 178
  25. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 154
  26. 2022DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulationcited by 137
  27. 2024RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Roboticscited by 136
  28. 2025RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concretecited by 135
  29. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 113
  30. 2025OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoningcited by 107
  31. 2019Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environmentscited by 90
  32. 2025DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Graspingcited by 89
  33. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88
  34. 2025Universal Actions for Enhanced Embodied Foundation Modelscited by 82
  35. 2024CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Drivingcited by 77
  36. 2024Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphscited by 73
  37. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 73
  38. 2025MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulationcited by 70

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 23.

38 papers.

Sort:

By area:

  1. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 179
  2. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  3. 2025VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layercited by 34
  4. 2025GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructionscited by 19
  5. 2025Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robotscited by 17
  6. 2025π_textttRL: Online RL Fine-tuning for Flow-based Vision-Language-Action Modelscited by 16
  7. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agentscited by 14
  8. 2026DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Modelscited by 12
  9. 2026Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflectioncited by 11
  10. 2026STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulationcited by 10
  11. 2025Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Modelscited by 9
  12. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
26 more
  1. 2025HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworkscited by 7
  2. 2025MetaVLA: Unified Meta Co-training For Efficient Embodied Adaptioncited by 5
  3. 2025VDRive: Leveraging Reinforced VLA and Diffusion Policy for End-to-end Autonomous Drivingcited by 5
  4. 2026AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignmentcited by 5
  5. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  6. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challengescited by 3
  7. 2026SELF-VLA: A Skill Enhanced Agentic Vision-Language-Action Framework for Contact-Rich Disassemblycited by 3
  8. 2026Information-Theoretic Constraints for Continual Vision-Language-Action Alignmentcited by 3
  9. 2026Listen, Look, Drive: Coupling Audio Instructions for User-aware VLA-based Autonomous Drivingcited by 2
  10. 2026Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learningcited by 2
  11. 2025Sigma: The Key for Vision-Language-Action Models toward Telepathic Alignmentcited by 1
  12. 2026Pedagogical Alignment for Vision-Language-Action Models: A Comprehensive Framework for Data, Architecture, and Evaluation in Educationcited by 1
  13. 2026Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoringcited by 1
  14. 2026RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Datacited by 1
  15. 2026PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action Policiescited by 1
  16. 2026WorldAgen: Unified State-Action Prediction with Test-Time World Model Trainingcited by 1
  17. 2025OpenTie: Open-vocabulary Sequential Rebar Tying Systemcited by 0
  18. 2026Grounding Sim-to-Real Generalization in Robotic Manipulation: An Empirical Study with Vision-Language-Action Modelscited by 0
  19. 2026Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planningcited by 0
  20. 2026S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Informationcited by 0
  21. 2026Trajectory Divergence Horizon Decision for Reliable Dual-Arm Surgical Subtask Manipulationcited by 0
  22. 2026Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Modelscited by 0
  23. 2026GloVLA: Let Geometry Move and Local VLA Interact for Robust Object-Centric Manipulation in Unstructured Environmentscited by 0
  24. 2026Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policiescited by 0
  25. 2026Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluationcited by 0
  26. 2026Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Roboticscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
  2. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Survey
  3. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  4. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
  5. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots
  6. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges
  7. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  8. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulation