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

• URL: http://arxiv.org/abs/2605.29562v1
• Date: Thu, 28 May 2026 08:14:08 GMT
• Title: VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
• Abstract summary: VLA-Pro is a plug-and-play framework designed to enhance cross-task generalization.<n>It stores task-relevant procedural memories at training time and transferring these memories during inference.<n>Experiments on RoboTwin, RLBench, and real-world manipulation tasks show that VLA-Pro consistently improves cross-task generalization.
• Score: 73.99344788183949
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• RotVLA: Rotational Latent Action for Vision-Language-Action Model [54.22746299071677]
  We introduce RotVLA, a VLA framework built on a continuous rotational latent action representation.<n>Latent actions are modeled as elements of SO(n), providing continuity, compositionality, and structured geometry aligned with real-world action dynamics.<n>RotVLA consists of a VLM backbone and a flow-matching action head, pretrained on large-scale cross-embodiment robotic datasets and human videos.
  arXiv  Detail & Related papers  (2026-05-13T11:58:02Z)
• RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark [49.16825786282095]
  Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks.<n>Existing robotic memory benchmarks still lack multimodal annotations for memory formation, provide limited task coverage and structural complexity, and remain restricted to simulation without real-world evaluation.<n>We address this gap with RoboMemArena, a large-scale benchmark of 26 tasks, with average trajectory lengths exceeding 1,000 steps per task and 68.9% of subtasks being memory-dependent.
  arXiv  Detail & Related papers  (2026-05-11T17:54:49Z)
• Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Tasks [9.55115186979077]
  We show a way to impart both spatial and temporal memory to a vision-language-action (VLA) model by incorporating a language scratchpad.<n>We evaluate this approach on a split of memory-dependent tasks from the ClevrSkills environment, on MemoryBench, and on a challenging real-world pick-and-place task.
  arXiv  Detail & Related papers  (2026-02-24T15:30:55Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)
• MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation [22.063033063941788]
  Memory-Augmented Prompting for Vision-Language-Action model (MAP-VLA) is a novel framework that empowers pre-trained VLA models with demonstration-derived memory prompts to augment action generation for long-horizon robotic manipulation tasks.<n>Results show that MAP-VLA delivers up to 7.0% absolute performance gains in the simulation benchmark and 25.0% on real robot evaluations for long-horizon tasks, surpassing the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-11-12T17:56:13Z)
• Memp: Exploring Agent Procedural Memory [72.41472703974935]
  Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.<n>We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions.<n>We show that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks.
  arXiv  Detail & Related papers  (2025-08-08T16:20:56Z)
• FindingDory: A Benchmark to Evaluate Memory in Embodied Agents [49.18498389833308]
  We introduce a new benchmark for long-range embodied tasks in the Habitat simulator.<n>This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness.
  arXiv  Detail & Related papers  (2025-06-18T17:06:28Z)
• Toward Task Generalization via Memory Augmentation in Meta-Reinforcement Learning [43.69919534800985]
  We introduce memory augmentation, a memory-based RL approach to improve task generalization.<n>Our approach leverages task-structured augmentations to simulate plausible out-of-distribution scenarios.<n>We demonstrate that our approach achieves zero-shot generalization to unseen tasks while maintaining robust in-distribution performance.
  arXiv  Detail & Related papers  (2025-02-03T17:00:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.