mlsanityData to 7 Oct 2026

A Survey on Vision-Language-Action Models for Embodied AI

arXiv 2405.14093 ↗First posted 23 May 2024cs.RO cs.CL cs.CVcited by 274

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

Abstract (arXiv)

Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language models (VLMs), a new category of multimodal models -- referred to as vision-language-action (VLA) models -- has emerged to address language-conditioned robotic tasks in embodied AI by leveraging their distinct ability to generate actions. The recent proliferation of VLAs necessitates a comprehensive survey to capture the rapidly evolving landscape. To this end, we present the first survey on VLAs for embodied AI. This work provides a detailed taxonomy of VLAs, organized into three major lines of research. The first line focuses on individual components of VLAs. The second line is dedicated to developing VLA-based control policies adept at predicting low-level actions. The third line comprises high-level task planners capable of decomposing long-horizon tasks into a sequence of subtasks, thereby guiding VLAs to follow more general user instructions. Furthermore, we provide an extensive summary of relevant resources, including datasets, simulators, and benchmarks. Finally, we discuss the challenges facing VLAs and outline promising future directions in embodied AI. A curated repository associated with this survey is available at: https://github.com/yueen-ma/Awesome-VLA.

Key facts. Cited by 274 papers in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 374 of its 481 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

374 of 481 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robots22 Dec
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 372

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020Language Models are Few-Shot Learnerscited by 32,199
  6. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  7. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  8. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  9. 2023GPT-4 Technical Reportcited by 18,132
  10. 2022Training language models to follow instructions with human feedbackcited by 15,712
  11. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  12. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
38 more
  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  9. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  10. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  11. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  12. 2017Graph Attention Networkscited by 8,854
  13. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  14. 2023Segment Anythingcited by 8,158
  15. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  16. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  17. 2023Visual Instruction Tuningcited by 7,792
  18. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  19. 2020End-to-End Object Detection with Transformerscited by 7,384
  20. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  21. 2017Mask R-CNNcited by 7,259
  22. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  23. 2017Inductive Representation Learning on Large Graphscited by 6,284
  24. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  25. 2022Scalable Diffusion Models with Transformerscited by 5,931
  26. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  27. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  28. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  29. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  30. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  31. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  32. 2017Squeeze-and-Excitation Networkscited by 4,763
  33. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  34. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  35. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  36. 2018How Powerful are Graph Neural Networks?cited by 4,355
  37. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  38. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337

50 most cited of 372 All 372 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 116; 2026: 145.

274 papers.

Sort:

By area:

  1. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 213
  2. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  3. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  4. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 166
  5. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Taskscited by 119
  6. 2025Improving Vision-Language-Action Model with Online Reinforcement Learningcited by 107
  7. 2025Agentic Large Language Models, a surveycited by 105
  8. 2025What Can RL Bring to VLA Generalization? An Empirical Studycited by 102
  9. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 94
  10. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  11. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  12. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
38 more
  1. 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learningcited by 69
  2. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  3. 2025Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenescited by 62
  4. 2024Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoningcited by 45
  5. 2025BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimizationcited by 37
  6. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  7. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 35
  8. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 34
  9. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  10. 2025AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPOcited by 33
  11. 2025VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layercited by 32
  12. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  13. 2025Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptancecited by 31
  14. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalizationcited by 29
  15. 2025VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Modelscited by 28
  16. 2025A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agentscited by 27
  17. 2025Large Language Models for Multi-Robot Systems: A Surveycited by 26
  18. 2025RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Modelscited by 26
  19. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 25
  20. 2024Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Modelscited by 24
  21. 2025Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variationscited by 24
  22. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelscited by 24
  23. 2024Large Multi-modal Models Can Interpret Features in Large Multi-modal Modelscited by 23
  24. 2025Embodied AI: From LLMs to World Modelscited by 23
  25. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  26. 2025RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedbackcited by 19
  27. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  28. 2024VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-usecited by 17
  29. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  30. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 17
  31. 2024GP-VLS: A general-purpose vision language model for surgerycited by 16
  32. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  33. 2025Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objectscited by 16
  34. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 16
  35. 2025Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulationcited by 15
  36. 2025RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulationcited by 15
  37. 2025Goal-VLA: Image-Generative VLMs as Object-Centric World Models Empowering Zero-shot Robot Manipulationcited by 15
  38. 2025Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inferencecited by 14

50 most cited of 274 All 274 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  2. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
  3. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
  4. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots
  5. 2025From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
  6. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Survey
  7. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  8. 2026Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data