mlsanityData to 14 Oct 2026

Survey of Vision-Language-Action Models for Embodied Manipulation

arXiv 2508.15201 ↗First posted 21 Aug 2025cs.RO cs.AIcited by 7

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

Abstract (arXiv)

Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in large foundation models, serve as universal robotic control frameworks that substantially improve agent-environment interaction capabilities in embodied intelligence systems. This expansion has broadened application scenarios for embodied AI robots. This survey comprehensively reviews VLA models for embodied manipulation. Firstly, it chronicles the developmental trajectory of VLA architectures. Subsequently, we conduct a detailed analysis of current research across 5 critical dimensions: VLA model structures, training datasets, pre-training methods, post-training methods, and model evaluation. Finally, we synthesize key challenges in VLA development and real-world deployment, while outlining promising future research directions.

Key facts. Cited by 7 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 168 of its 194 references that are in the map. First posted on arXiv 21 Aug 2025.

Builds on

168 of 194 references.

Closest ancestors · 26

Same direction, newest first

  1. 2025GR-3 Technical Report21 Jul
  2. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review14 Jul
  3. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends26 Jun
  4. 2025From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models11 Jun
  5. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  6. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better29 May
  7. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Model27 May
  8. 2025Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization21 May
  9. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges7 May
  10. 2025OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation6 May
  11. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks28 Apr
  12. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
14 more
  1. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  2. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  3. 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent31 Jan
  4. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots18 Dec
  5. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation29 Nov
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  7. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation10 Oct
  8. 2024VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation19 Sep
  9. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation19 Sep
  10. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers12 Sep
  11. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  12. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation6 Jun
  13. 2024A Survey on Vision-Language-Action Models for Embodied AI23 May
  14. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 142

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  10. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
38 more
  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  2. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  3. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  4. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  5. 2019Towards VQA Models That Can Readcited by 1,718
  6. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  7. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  8. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  9. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  10. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  11. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  12. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  13. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  14. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  15. 2022A Generalist Agentcited by 808
  16. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  17. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
  18. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  19. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  20. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  21. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  22. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  23. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  24. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  25. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  26. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  27. 2023Learning Universal Policies via Text-Guided Video Generationcited by 522
  28. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  29. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 518
  30. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 495
  31. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 490
  32. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  33. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 410
  34. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 407
  35. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 405
  36. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 394
  37. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 384
  38. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 367

50 most cited of 142 All 142 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 179
  2. 2026WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RLcited by 50
  3. 2025Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challengescited by 4
  4. 2026Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Modelcited by 4
  5. 2026E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenescited by 4
  6. 2026ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptationcited by 2
  7. 2026ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
  2. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
  3. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
  4. 202510 Open Challenges Steering the Future of Vision-Language-Action Models
  5. 2025From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems
  6. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Survey
  7. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
  8. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulation