mlsanityData to 7 Oct 2026

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models

arXiv 2605.29562 ↗First posted 28 May 2026cs.RO cs.AI cs.CVcited by 2

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

Abstract (arXiv)

Vision-Language-Action~(VLA) models have shown strong potential for general-purpose robotic manipulation, yet they still struggle to generalize to unseen tasks that necessitate transferring relevant experience across objects, scenes, and action patterns. This paper proposes VLA-Pro, a plug-and-play framework designed to enhance cross-task generalization by storing task-relevant procedural memories at training time and transferring these memories during inference. Specifically, VLA-Pro stores task-specific LoRA adapters as parameterized procedural memories during training. At inference time, VLA-Pro retrieves relevant procedural memories based on the current multi-modal context and dynamically fuses these memories for generating the current action chunk. Experiments on RoboTwin, RLBench, and real-world manipulation tasks show that VLA-Pro consistently improves cross-task generalization across multiple backbones, achieving up to a 207% relative improvement in simulation and increasing real-world success rate from 5.8% to 65.0%. These results suggest that procedural memory retrieval and adaptation provide an effective mechanism for transferring manipulation experience to novel tasks while preserving modularity and execution stability.

Key facts. Cited by 2 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 47 of its 55 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

47 of 55 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies4 Mar
  2. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation26 Aug
  3. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation23 Jul

Other references · 44

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  4. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  5. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  6. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  7. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  8. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  9. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  10. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  11. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
  12. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 252
32 more
  1. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 135
  2. 2025ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceivercited by 80
  3. 2025RynnVLA-002: A Unified Vision-Language-Action and World Modelcited by 70
  4. 2024Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulationcited by 69
  5. 2024RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulationcited by 55
  6. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  7. 2025OmniRouter: Budget and Performance Controllable Multi-LLM Routingcited by 35
  8. 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulationcited by 33
  9. 2025Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalizationcited by 31
  10. 2024Retrieval-Augmented Embodied Agentscited by 30
  11. 2026FluxMem: Adaptive Hierarchical Memory for Streaming Video Understandingcited by 26
  12. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelscited by 24
  13. 2023Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMscited by 19
  14. 2025RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Modelscited by 19
  15. 2024Keypoint Abstraction using Large Models for Object-Relative Imitation Learningcited by 18
  16. 2025Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidancecited by 18
  17. 2025MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agentcited by 15
  18. 2026AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robotscited by 15
  19. 2025DeepSieve: Information Sieving via LLM-as-a-Knowledge-Routercited by 13
  20. 2025RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulationcited by 12
  21. 2026ST4VLA: Spatially Guided Training for Vision-Language-Action Modelscited by 8
  22. 2026CORAL: Scalable Multi-Task Robot Learning via LoRA Expertscited by 8
  23. 2023Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Push Manipulation by Mobile Robotscited by 6
  24. 2026Adaptive Capacity Allocation for Vision Language Action Fine-tuningcited by 6
  25. 2026Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progresscited by 6
  26. 2025COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy Learningcited by 5
  27. 2026RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptationcited by 3
  28. 2026From Local Corrections to Generalized Skills: Improving Neuro-Symbolic Policies with MEMOcited by 2
  29. 20263D-Anchored Lookahead Planning for Persistent Robotic Scene Memory via World-Model-Based MCTScited by 2
  30. 2025QueryAdapter: Rapid Adaptation of Vision-Language Models in Response to Natural Language Queriescited by 1
  31. 2025Zero-Shot Vehicle Model Recognition via Text-Based Retrieval-Augmented Generationcited by 1
  32. 2026Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Retrieve in Time, Correct in Frequencycited by 0
  2. 2026OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation
  2. 2026Inline Memory Meets Reusable Skills: Memory-centric Framework for Vision-Language-Action Model
  3. 2026MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation
  4. 2025EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation
  5. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  6. 2026RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
  7. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  8. 2025Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion