RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models

• URL: http://arxiv.org/abs/2606.23617v1
• Date: Mon, 22 Jun 2026 17:12:50 GMT
• Title: RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models
• Abstract summary: We propose an active, continual learning paradigm for Vision-Language-Action (VLA) models.<n>We demonstrate that active, uncertainty-guided data collection leads to more efficient fine-tuning than when using passively-collected demonstrations.<n>We also find that fine-tuning only on actively-collected recovery data leads to catastrophic forgetting.
• Score: 1.7157586976839874
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language-Action (VLA) models are commonly fine-tuned through passive imitation learning, where additional demonstrations are collected for tasks where the policy performs poorly. This approach incurs several downsides: it requires the robot to fail before data collection is triggered, provides little guidance about which states require supervision, and wastes demonstrator effort on redundant parts of the task where the policy already performs well. In this paper, we propose an active, continual learning paradigm for VLAs. We demonstrate that active, uncertainty-guided data collection leads to more efficient fine-tuning than when using passively-collected demonstrations. However, we also find that fine-tuning only on actively-collected recovery data leads to catastrophic forgetting. We evaluate techniques for continual learning, including replay-based data mixing and elastic weight consolidation, and identify tradeoffs between plasticity to uncertainty-guided recovery data and retention of previously learned behaviors. Overall, our work contributes an empirical study of active continual learning for autoregressive VLAs, establishing that uncertainty-guided recovery demonstrations can improve adaptation efficiency while also revealing open challenges when targeted new data is incorporated into large robot policies.

Related papers

• Unleashing More Actions via Action Compositional Training for VLA Models [23.837636418111035]
  Vision-Language-Action models excel at robotic manipulation, driven by the scale and diversity of demonstration data.<n>We propose ACT-VLA (Action Compositional Training for VLA Models), an offline data augmentation framework.<n>By eliminating additional manual data collection, our method automatically expands the training distribution and mitigates overfitting.
  arXiv  Detail & Related papers  (2026-07-01T02:48:17Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning [51.07663354001582]
  Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task.<n>We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches.<n>We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods.
  arXiv  Detail & Related papers  (2025-12-01T15:56:00Z)
• RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation [35.01431111972725]
  Vision-Language-Action models (VLAs) have demonstrated remarkable performance on complex robotic manipulation tasks through imitation learning.<n>We propose an automated OOD data augmentation framework named RESample through exploratory sampling.<n>We conduct extensive experiments on the LIBERO benchmark as well as real-world robotic manipulation tasks, demonstrating that RESample consistently improves the stability and generalization ability of VLA models.
  arXiv  Detail & Related papers  (2025-10-20T15:21:12Z)
• Reinforcement Learning via Implicit Imitation Guidance [49.88208134736617]
  A natural approach is to incorporate an imitation learning objective, either as regularization during training or to acquire a reference policy.<n>We propose to use prior data solely for guiding exploration via noise added to the policy, sidestepping the need for explicit behavior cloning constraints.<n>Our approach achieves up to 2-3x improvement over prior reinforcement learning from offline methods across seven simulated continuous control tasks.
  arXiv  Detail & Related papers  (2025-06-09T07:32:52Z)
• Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey [7.428771158422113]
  Supervised learning relies on data annotation which usually is time-consuming and therefore expensive.<n>A longstanding strategy to reduce annotation costs is active learning, in which a human annotates only data instances deemed informative by a model.<n>We conduct an online survey in the NLP community to collect previously intangible insights on current implementation practices, common obstacles in application, and future prospects in active learning.
  arXiv  Detail & Related papers  (2025-03-12T18:00:04Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning [17.092640837991883]
  Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data. We show how the combination of a reverse curriculum and forward curriculum in our method, RFCL, enables significant improvements in demonstration and sample efficiency.
  arXiv  Detail & Related papers  (2024-05-06T11:33:12Z)
• Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes [72.75421975804132]
  Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting. We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem. Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
  arXiv  Detail & Related papers  (2023-09-11T14:16:37Z)
• ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
  We introduce Action-Aware Embodied Learning for Perception (ALP) ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. We show that ALP outperforms existing baselines in several downstream perception tasks.
  arXiv  Detail & Related papers  (2023-06-16T21:51:04Z)
• Data Poisoning Attack Aiming the Vulnerability of Continual Learning [25.480762565632332]
  We present a simple task-specific data poisoning attack that can be used in the learning process of a new task. We experiment with the attack on the two representative regularization-based continual learning methods.
  arXiv  Detail & Related papers  (2022-11-29T02:28:05Z)
• Responsible Active Learning via Human-in-the-loop Peer Study [88.01358655203441]
  We propose a responsible active learning method, namely Peer Study Learning (PSL), to simultaneously preserve data privacy and improve model stability. We first introduce a human-in-the-loop teacher-student architecture to isolate unlabelled data from the task learner (teacher) on the cloud-side. During training, the task learner instructs the light-weight active learner which then provides feedback on the active sampling criterion.
  arXiv  Detail & Related papers  (2022-11-24T13:18:27Z)

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.