mlsanityData to 14 Oct 2026

Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation

arXiv 2508.19958 ↗First posted 27 Aug 2025cs.ROcited by 48

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

Abstract (arXiv)

Vision-Language-Action (VLA) models have become a cornerstone in robotic policy learning, leveraging large-scale multimodal data for robust and scalable control. However, existing VLA frameworks primarily address short-horizon tasks, and their effectiveness on long-horizon, multi-step robotic manipulation remains limited due to challenges in skill chaining and subtask dependencies. In this work, we introduce Long-VLA, the first end-to-end VLA model specifically designed for long-horizon robotic tasks. Our approach features a novel phase-aware input masking strategy that adaptively segments each subtask into moving and interaction phases, enabling the model to focus on phase-relevant sensory cues and enhancing subtask compatibility. This unified strategy preserves the scalability and data efficiency of VLA training, and our architecture-agnostic module can be seamlessly integrated into existing VLA models. We further propose the L-CALVIN benchmark to systematically evaluate long-horizon manipulation. Extensive experiments on both simulated and real-world tasks demonstrate that Long-VLA significantly outperforms prior state-of-the-art methods, establishing a new baseline for long-horizon robotic control.

Key facts. Cited by 48 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 51 of its 59 references that are in the map. First posted on arXiv 27 Aug 2025.

Builds on

51 of 59 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions16 May
  2. 2025OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation6 May
  3. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  4. 2025VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation19 Feb
  5. 2025GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation13 Feb
  6. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  7. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots18 Dec
  8. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation19 Sep
  9. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  10. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robots22 Dec
  11. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  5. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  6. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  7. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  8. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  9. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  10. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  11. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  12. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
28 more
  1. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 349
  2. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 161
  3. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 134
  4. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Executioncited by 117
  5. 2023Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Modelscited by 91
  6. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88
  7. 2023Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidancecited by 86
  8. 2024Manipulate-Anything: Automating Real-World Robots using Vision-Language Modelscited by 83
  9. 2024Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Taskscited by 52
  10. 2023Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulationcited by 49
  11. 2025ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learningcited by 47
  12. 2021Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularizationcited by 46
  13. 2025Humanoid-VLA: Towards Universal Humanoid Control with Visual Integrationcited by 45
  14. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decodingcited by 38
  15. 2024GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robotcited by 29
  16. 2024CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Predictioncited by 27
  17. 2025MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Modelscited by 27
  18. 2024Local Policies Enable Zero-shot Long-horizon Manipulationcited by 22
  19. 2022Generating Executable Action Plans with Environmentally-Aware Language Modelscited by 21
  20. 2024RH20T-P: A Primitive-Level Robotic Dataset Towards Composable Generalization Agentscited by 20
  21. 2022STAP: Sequencing Task-Agnostic Policiescited by 18
  22. 2024Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitationcited by 18
  23. 2023Skill Transformer: A Monolithic Policy for Mobile Manipulationcited by 16
  24. 2025Learning Compositional Behaviors from Demonstration and Languagecited by 15
  25. 2024SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulationcited by 11
  26. 2024QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learningcited by 9
  27. 2025Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transportcited by 6
  28. 2024A Backbone for Long-Horizon Robot Task Understandingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 41.

48 papers.

Sort:

By area:

  1. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 145
  2. 2025VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulatorscited by 67
  3. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  4. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Modelscited by 22
  5. 2025QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Modelscited by 21
  6. 2026Current Agents Fail to Leverage World Model as Tool for Foresightcited by 17
  7. 2026CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decodingcited by 14
  8. 2026LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policiescited by 14
  9. 2026HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulationcited by 10
  10. 2026Long-Horizon Manipulation via Trace-Conditioned VLA Planningcited by 9
  11. 2026Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Modelscited by 9
  12. 2026μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Modelscited by 8
36 more
  1. 2026PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidancecited by 6
  2. 2026Veo-Act: Enhancing VLA Policies with Frontier Video Modelscited by 5
  3. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  4. 2026Recursive Belief Vision Language Action Modelscited by 4
  5. 2025PhysicalAgent: Towards General Cognitive Robotics with Foundation World Modelscited by 3
  6. 2025UnderwaterVLA: Dual-brain Vision-Language-Action architecture for Autonomous Underwater Navigationcited by 3
  7. 2026Generalizable Dense Reward for Long-Horizon Robotic Taskscited by 3
  8. 2026World Pilot: Steering Vision-Language-Action Models with World-Action Priorscited by 3
  9. 2026Unleashing More Actions via Action Compositional Training for VLA Modelscited by 3
  10. 2026AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experimentscited by 2
  11. 2026Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generationcited by 2
  12. 2026VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Modelscited by 2
  13. 2026FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuningcited by 2
  14. 2026WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot Manipulationcited by 2
  15. 2026Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learningcited by 2
  16. 2026In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Usecited by 2
  17. 2026SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulationcited by 2
  18. 2026Reshaping Action Error Distributions for Reliable Vision-Language-Action Modelscited by 1
  19. 2026Selective Perception for Robot: Task-Aware Attention in Multimodal VLAcited by 1
  20. 2026Habilis-β: A Fast-Motion and Long-Lasting On-Device Vision-Language-Action Modelcited by 1
  21. 2026Make Your VLA More Robust Without More Data By Interleaving Motion Planningcited by 1
  22. 2026ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curationcited by 1
  23. 2026PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action Policiescited by 1
  24. 2026FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Modelcited by 1
  25. 2026hint2: Hierarchical World Models for Inference-Time Temporal Logic Guidancecited by 1
  26. 2026AdaHVLA: Adaptive Harnesses for Long-Horizon Vision-Language-Action Executioncited by 1
  27. 2026MotionBits: Video Segmentation through Motion-Level Analysis of Rigid Bodiescited by 0
  28. 2026AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulationcited by 0
  29. 2026TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulationcited by 0
  30. 2026UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modelingcited by 0
  31. 2026Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulationcited by 0
  32. 2026Task-Specified Active Metrological Inspection with Measurement-Steered VLA Manipulation and Deterministic Evidence Gatingcited by 0
  33. 2026From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluationcited by 0
  34. 2026GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policiescited by 0
  35. 2026Latent evolving World Action Modelcited by 0
  36. 2026FailPatch: Failure Residual Patching for Vision-Language-Action Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
  2. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  3. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  4. 2026AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
  5. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  6. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
  7. 2026D2-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
  8. 2026S2-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation