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

arXiv: https://arxiv.org/abs/2606.23617 · HTML: https://mlsanity.com/paper/2606.23617/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)
- Offline RL and imitation learning from data / [Language-conditioned policies and VLAs](https://mlsanity.com/offlinerl/language-conditioned-policies-and-vlas/)

## Builds on (most cited first, 15 of 15)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning](https://mlsanity.com/paper/1807.08364/) (2018)
- [Gemini Robotics: Bringing AI into the Physical World](https://mlsanity.com/paper/2503.20020/) (2025)
- [Diff-DAgger: Uncertainty Estimation with Diffusion Policy for Robotic Manipulation](https://mlsanity.com/paper/2410.14868/) (2024)
- [Uncertainty-Aware Data Aggregation for Deep Imitation Learning](https://mlsanity.com/paper/1905.02780/) (2019)
- [Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback](https://mlsanity.com/paper/2410.08852/) (2024)
- [INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01389/) (2025)

## Built on by (most cited first, 3 of 3)

- [BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning](https://mlsanity.com/paper/2607.29302/) (2026)
- [FAN: Foresight Action Normalization for Continual Adaptation of Vision-Language-Action Models](https://mlsanity.com/paper/2609.21358/) (2026)
- [Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning](https://mlsanity.com/paper/2610.05882/) (2026)

## Abstract (arXiv)

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.