# SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists

arXiv: https://arxiv.org/abs/2609.22854 · HTML: https://mlsanity.com/paper/2609.22854/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 26 of its 26 references that are in the map.
- First posted on arXiv 19 Sep 2026.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 26 of 26)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [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)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [xLSTM: Extended Long Short-Term Memory](https://mlsanity.com/paper/2405.04517/) (2024)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning](https://mlsanity.com/paper/2502.10550/) (2025)
- [ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries](https://mlsanity.com/paper/2603.12942/) (2026)
- [Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective](https://mlsanity.com/paper/2511.11478/) (2025)
- [A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks](https://mlsanity.com/paper/2410.22391/) (2024)
- [X-IL: Exploring the Design Space of Imitation Learning Policies](https://mlsanity.com/paper/2502.12330/) (2025)
- [SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation](https://mlsanity.com/paper/2511.06754/) (2025)
- [μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models](https://mlsanity.com/paper/2606.12497/) (2026)
- [MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation](https://mlsanity.com/paper/2606.20679/) (2026)
- [2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation](https://mlsanity.com/paper/2609.11308/) (2026)

## Abstract (arXiv)

Vision-language-action models often predict actions from only the current observation, which can leave tasks involving object occlusion or visually identical objects ambiguous without episode history. The usual countermeasure, widening the observation window, turns the horizon into a hyperparameter and lets per-step cost grow with it. We instead capture the episode in a recurrent state. SmoLSTM couples a frozen 256M-parameter SmolVLM backbone to a matrix-memory LSTM control layer in which observation tokens and action queries are unified in a single causal stream that is never reset throughout the entire episode. Recurrent-state storage is therefore O(1) in episode length. A flow-matching action head predicts chunks of 10 end-effector pose deltas and gripper commands at each control step. Our single policy, trained jointly on 7,461 demonstrations across 140 tasks and evaluated on held-out initial states, performs best, reaching 85.1% subgoal coverage and 77.5% full-task success on LIBERO-Mem with 0.04B trainable parameters, surpassing both the benchmark's own object-centric baseline and recent memory-based approaches. Resetting the recurrent state at every control step reduces full-task success to 7.0%, showing that the trained policy relies on context carried between decisions. The same model achieves 79.6% average success on standard LIBERO.