mlsanityData to 14 Oct 2026

Pure Vision Language Action (VLA) Models: A Comprehensive Survey

arXiv 2509.19012 ↗First posted 23 Sep 2025cs.RO cs.AIcited by 49

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

also in 1 more
Abstract (arXiv)

The emergence of Vision Language Action (VLA) models marks a paradigm shift from traditional policy-based control to generalized robotics, reframing Vision Language Models (VLMs) from passive sequence generators into active agents for manipulation and decision-making in complex, dynamic environments. This survey delves into advanced VLA methods, aiming to provide a clear taxonomy and a systematic, comprehensive review of existing research. It presents a comprehensive analysis of VLA applications across different scenarios and classifies VLA approaches into several paradigms: autoregression-based, diffusion-based, reinforcement-based, hybrid, and specialized methods; while examining their motivations, core strategies, and implementations in detail. In addition, foundational datasets, benchmarks, and simulation platforms are introduced. Building on the current VLA landscape, the review further proposes perspectives on key challenges and future directions to advance research in VLA models and generalizable robotics. By synthesizing insights from over three hundred recent studies, this survey maps the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose VLA methods.

Key facts. Cited by 49 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. Builds on 287 of its 311 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

287 of 311 references.

Closest ancestors · 33

Same direction, newest first

  1. 2025EdgeVLA: Efficient Vision-Language-Action Models18 Jul
  2. 2025CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling24 Jun
  3. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models9 Jun
  4. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  5. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better29 May
  6. 2025InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning20 May
  7. 2025VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation14 May
  8. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar
  9. 2025MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation26 Mar
  10. 2025CubeRobot: Grounding Language in Rubik's Cube Manipulation via Vision-Language Model25 Mar
  11. 2025JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse20 Mar
  12. 2025TLA: Tactile-Language-Action Model for Contact-Rich Manipulation11 Mar
21 more
  1. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Models10 Mar
  2. 2025RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete28 Feb
  3. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  4. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  5. 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent31 Jan
  6. 2025Improving Vision-Language-Action Model with Online Reinforcement Learning28 Jan
  7. 2024ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics27 Nov
  8. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution4 Nov
  9. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers12 Sep
  10. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul
  11. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policy28 Jun
  12. 2024RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation27 Jun
  13. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics15 Jun
  14. 2024Grounding Multimodal Large Language Models in Actions12 Jun
  15. 2024Yell At Your Robot: Improving On-the-Fly from Language Corrections19 Mar
  16. 2024Vision-Language Models Provide Promptable Representations for Reinforcement Learning5 Feb
  17. 2023Vision-Language Foundation Models as Effective Robot Imitators2 Nov
  18. 2023Physically Grounded Vision-Language Models for Robotic Manipulation5 Sep
  19. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul
  20. 2023PaLM-E: An Embodied Multimodal Language Model6 Mar
  21. 2023Open-World Object Manipulation using Pre-trained Vision-Language Models2 Mar

Other references · 254

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2017Proximal Policy Optimization Algorithmscited by 15,215
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  7. 2023Visual Instruction Tuningcited by 7,869
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  9. 2025Qwen2.5-VL Technical Reportcited by 5,587
  10. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  12. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
38 more
  1. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  7. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  8. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  9. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  10. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  11. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  12. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  13. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
  14. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  15. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  16. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  17. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  18. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  19. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  20. 2018DeepMind Control Suitecited by 956
  21. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  22. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  23. 2022A Generalist Agentcited by 808
  24. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  25. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  26. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
  27. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  28. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  29. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  30. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  31. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  32. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  33. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  34. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  35. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  36. 2023Learning Universal Policies via Text-Guided Video Generationcited by 522
  37. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  38. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511

50 most cited of 254 All 254 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 39.

49 papers.

Sort:

By area:

  1. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  2. 2025VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layercited by 34
  3. 2025Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Toolscited by 26
  4. 2026FASTER: Rethinking Real-Time Flow VLAscited by 21
  5. 2025When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Modelscited by 20
  6. 2025Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Drivingcited by 14
  7. 2026Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanismscited by 13
  8. 2026DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Modelscited by 12
  9. 2026STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbationscited by 10
  10. 2026What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generationcited by 8
  11. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Enginescited by 8
  12. 2025CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Modelcited by 7
37 more
  1. 2026RL-VLA3: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Trainingcited by 7
  2. 2026Mean-Flow based One-Step Vision-Language-Actioncited by 7
  3. 2026Point Tracking Improves World Action Modelscited by 7
  4. 2026VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoningcited by 6
  5. 2025ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Modelscited by 5
  6. 2026VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptationcited by 5
  7. 2026Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLAcited by 5
  8. 2026Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rolloutscited by 5
  9. 2026FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulationcited by 5
  10. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  11. 2026Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Trainingcited by 4
  12. 2026Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptationcited by 4
  13. 2025Dejavu: Towards Experience Feedback Learning for Embodied Intelligencecited by 3
  14. 2026Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Modelscited by 2
  15. 2026IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Toolscited by 2
  16. 2025LiMT: A Multi-task Liver Image Benchmark Datasetcited by 1
  17. 2026Keyframe-Guided Structured Rewards for Reinforcement Learning in Long-Horizon Laboratory Roboticscited by 1
  18. 2026ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Modelscited by 1
  19. 2026CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchorscited by 1
  20. 2026D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Modelscited by 1
  21. 2026BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Modelscited by 1
  22. 2026Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoningcited by 1
  23. 2026UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Modelscited by 1
  24. 2026PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policiescited by 1
  25. 2026S2-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulationcited by 1
  26. 2026WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Drivingcited by 1
  27. 2026EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraintscited by 1
  28. 2026Safety Case Patterns for VLA-based driving systems: Insights from SimLingocited by 0
  29. 2026SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for Laparoscopic Surgical Roboticscited by 0
  30. 2026PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulationcited by 0
  31. 2026Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAscited by 0
  32. 2026Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automationcited by 0
  33. 2026FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflowscited by 0
  34. 2026Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Modelscited by 0
  35. 2026KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Modelscited by 0
  36. 2026VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Predictioncited by 0
  37. 2026X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

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