mlsanityData to 7 Oct 2026

OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning

arXiv 2505.11917 ↗First posted 17 May 2025cs.ROcited by 105

On the map: Vision-language-action models → Reasoning and chain-of-thought in VLA

Abstract (arXiv)

General-purpose robots capable of performing diverse tasks require synergistic reasoning and acting capabilities. However, recent dual-system approaches, which separate high-level reasoning from low-level acting, often suffer from challenges such as limited mutual understanding of capabilities between systems and latency issues. This paper introduces OneTwoVLA, a single unified vision-language-action model that can perform both acting (System One) and reasoning (System Two). Crucially, OneTwoVLA adaptively switches between two modes: explicitly reasoning at critical moments during task execution, and generating actions based on the most recent reasoning at other times. To further unlock OneTwoVLA's reasoning and generalization capabilities, we design a scalable pipeline for synthesizing embodied reasoning-centric vision-language data, used for co-training with robot data. We validate OneTwoVLA's effectiveness through extensive experiments, highlighting its superior performance across four key capabilities: long-horizon task planning, error detection and recovery, natural human-robot interaction, and generalizable visual grounding, enabling the model to perform long-horizon, highly dexterous manipulation tasks such as making hotpot or mixing cocktails.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models. Builds on 63 of its 89 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

63 of 89 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Training Strategies for Efficient Embodied Reasoning13 May
  2. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar
  3. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model20 Feb
  4. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul

Other references · 59

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  11. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  12. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
38 more
  1. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  2. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  3. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  5. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  6. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  7. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  8. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 718
  9. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  10. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  11. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  12. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  13. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 468
  14. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  15. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  16. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  17. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 277
  18. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 276
  19. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 268
  20. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Roboticscited by 242
  21. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  22. 2024RT-H: Action Hierarchies Using Languagecited by 204
  23. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 202
  24. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 191
  25. 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
  26. 2023Open-World Object Manipulation using Pre-trained Vision-Language Modelscited by 155
  27. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 144
  28. 2023PaLI-3 Vision Language Models: Smaller, Faster, Strongercited by 125
  29. 2025HAMSTER: Hierarchical Action Models For Open-World Robot Manipulationcited by 125
  30. 2024Yell At Your Robot: Improving On-the-Fly from Language Correctionscited by 123
  31. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  32. 2024CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Modelscited by 97
  33. 2018Robot Learning in Homes: Improving Generalization and Reducing Dataset Biascited by 75
  34. 2023Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agentscited by 66
  35. 2024Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigationcited by 60
  36. 2018Interactive Visual Grounding of Referring Expressions for Human-Robot Interactioncited by 55
  37. 2025OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extractioncited by 54
  38. 2024Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learningcited by 44

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 44; 2026: 61.

105 papers.

Sort:

By area:

  1. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  2. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  3. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 104
  4. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 83
  5. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  6. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  7. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  8. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  9. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 55
  10. 2025Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgettingcited by 52
  11. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 48
  12. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
38 more
  1. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Reviewcited by 38
  2. 2025RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correctioncited by 37
  3. 2025OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensingcited by 37
  4. 2025Don't Blind Your VLA: Aligning Visual Representations for OOD Generalizationcited by 34
  5. 2025EO-1: An Open Unified Embodied Foundation Model for General Robot Controlcited by 30
  6. 2025VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Modelscited by 28
  7. 2026LaST0: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Modelcited by 28
  8. 2025Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verificationcited by 25
  9. 2025RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulationcited by 24
  10. 2025Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoningcited by 21
  11. 2026A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulationcited by 20
  12. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Modelscited by 19
  13. 2026Learning Native Continuation for Action Chunking Flow Policiescited by 18
  14. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  15. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 17
  16. 2025Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalizationcited by 16
  17. 2025Do You Need Proprioceptive States in Visuomotor Policies?cited by 16
  18. 2025RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Modelcited by 16
  19. 2026AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robotscited by 15
  20. 2025ManualVLA: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulationcited by 13
  21. 2025Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modelingcited by 13
  22. 2026Stable Language Guidance for Vision-Language-Action Modelscited by 13
  23. 2026RoboTTT: Context Scaling for Robot Policiescited by 13
  24. 2025Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generationcited by 12
  25. 2025MM-ACT: Learn from Multimodal Parallel Generation to Actcited by 12
  26. 2026RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulationcited by 12
  27. 2025DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Actioncited by 11
  28. 2026Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrationscited by 11
  29. 2026DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Drivingcited by 11
  30. 2026Wall-OSS-0.5 Technical Reportcited by 11
  31. 2025PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligencecited by 10
  32. 2025Point What You Mean: Visually Grounded Instruction Policycited by 10
  33. 2026HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Modelscited by 10
  34. 2025METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Modelcited by 9
  35. 2026Demystifying Action Space Design for Robotic Manipulation Policiescited by 9
  36. 2026VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Modelcited by 9
  37. 2026AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Modelscited by 9
  38. 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environmentscited by 8

50 most cited of 105 All 105 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Mind to Hand: Purposeful Robotic Control via Embodied Reasoning
  2. 2026OneVLA: A Unified Framework for Embodied Tasks
  3. 2025MoTVLA: A Vision-Language-Action Model with Unified Fast-Slow Reasoning
  4. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Action
  5. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
  6. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
  7. 2026ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning
  8. 2025From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation