# ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and Retrieval

arXiv: https://arxiv.org/abs/2511.06202 · HTML: https://mlsanity.com/paper/2511.06202/

## Key facts

- Cited by 7 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 31 of its 38 references that are in the map.
- First posted on arXiv 9 Nov 2025.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)
- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 31)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation](https://mlsanity.com/paper/2502.05485/) (2025)
- [Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers](https://mlsanity.com/paper/2404.07220/) (2024)
- [SAFE: Multitask Failure Detection for Vision-Language-Action Models](https://mlsanity.com/paper/2506.09937/) (2025)
- [Retrieval-Augmented Reinforcement Learning](https://mlsanity.com/paper/2202.08417/) (2022)
- [Parametric Retrieval Augmented Generation](https://mlsanity.com/paper/2501.15915/) (2025)
- [Retrieval-Augmented Embodied Agents](https://mlsanity.com/paper/2404.11699/) (2024)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)

## Built on by (most cited first, 7 of 7)

- [Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation](https://mlsanity.com/paper/2606.02486/) (2026)
- [Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs](https://mlsanity.com/paper/2605.10094/) (2026)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [Information-Theoretic Constraints for Continual Vision-Language-Action Alignment](https://mlsanity.com/paper/2603.13335/) (2026)
- [Joint Learning of Depth, Pose, and Local Radiance Field for Large Scale Monocular 3D Reconstruction](https://mlsanity.com/paper/2512.18237/) (2025)
- [Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation](https://mlsanity.com/paper/2608.19490/) (2026)
- [Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models](https://mlsanity.com/paper/2608.24042/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models like OpenVLA demonstrate impressive zero-shot generalization across robotic manipulation tasks but struggle to adapt to specific deployment environments where consistent high performance on a limited set of tasks is more valuable than broad generalization. We present EXPierence replayed, REtrieval augmented, Specialized VLA (ExpReS-VLA), a method that enables rapid on-device adaptation of pre-trained VLAs to target domains while preventing catastrophic forgetting through compressed experience replay and retrieval-augmented generation. Our approach maintains a memory-efficient buffer by storing extracted embeddings from OpenVLA's frozen vision backbone, reducing storage requirements by 97% compared to raw image-action pairs. During deployment, ExpReS-VLA retrieves the k most similar past experiences using cosine similarity to augment training batches, while a prioritized experience replay buffer preserves recently successful trajectories. To leverage failed attempts, we introduce Thresholded Hybrid Contrastive Loss (THCL), enabling the model to learn from both successful and unsuccessful demonstrations. Experiments on the LIBERO benchmark show improvements from 82.6% to 93.1% on spatial reasoning and 61% to 72.3% on long-horizon tasks over base OpenVLA, with gains across architectures including π0 (+3.2 points) and OpenVLA-OFT (+1.7 points). Physical robot experiments across five tasks demonstrate 98% success on both in-distribution and out-of-distribution conditions, improving from 84.7% and 32% respectively for naive fine-tuning. Adaptation completes in 31 seconds using 12 demonstrations on a single RTX 5090.