# TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2606.03127 · HTML: https://mlsanity.com/paper/2606.03127/

## Key facts

- Cited by 9 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 23 of its 32 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 23 of 23)

- [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)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning](https://mlsanity.com/paper/2507.16815/) (2025)
- [Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers](https://mlsanity.com/paper/2409.20537/) (2024)
- [Magma: A Foundation Model for Multimodal AI Agents](https://mlsanity.com/paper/2502.13130/) (2025)
- [π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities](https://mlsanity.com/paper/2604.15483/) (2026)
- [Yell At Your Robot: Improving On-the-Fly from Language Corrections](https://mlsanity.com/paper/2403.12910/) (2024)
- [Self-Supervised Policy Adaptation during Deployment](https://mlsanity.com/paper/2007.04309/) (2020)
- [InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation](https://mlsanity.com/paper/2507.17520/) (2025)
- [Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning](https://mlsanity.com/paper/2412.11974/) (2024)
- [OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning](https://mlsanity.com/paper/2512.13100/) (2025)

## Built on by (most cited first, 9 of 9)

- [Self-Evolving Embodied Agents via Skill-Harness Evolution](https://mlsanity.com/paper/2608.11350/) (2026)
- [An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond](https://mlsanity.com/paper/2609.24170/) (2026)
- [StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models](https://mlsanity.com/paper/2608.11671/) (2026)
- [VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction](https://mlsanity.com/paper/2608.09448/) (2026)
- [Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning](https://mlsanity.com/paper/2607.08837/) (2026)
- [PredVLA: Predictive Sensorimotor Modeling for Sub-Million-Parameter Robot Manipulation](https://mlsanity.com/paper/2608.26673/) (2026)
- [Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution](https://mlsanity.com/paper/2610.07946/) (2026)
- [Juno: Taming Predictive Latents for Vision-Language-Action Models](https://mlsanity.com/paper/2610.09940/) (2026)
- [Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies](https://mlsanity.com/paper/2610.14588/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time. Recent VLA models suggest that prompts can serve as an efficient interface for steering policy behavior, but existing prompt-based steering typically relies on external guidance. This raises a natural question: can test-time training (TTT) for VLA be achieved by optimizing a prompt, so that the steering interface itself can be learned and adapted from interaction? We address this question with TTT-VLA, a test-time training framework based on Latent Prompt Optimization (LPO). During training, the latent prompt is learned with an additional proxy task, providing an extra learned conditioning signal for policy learning. At test time, TTT is performed by collecting interaction data from the current environment and optimizing only the latent prompt on those data using the proxy task's self-supervised signal, without modifying the policy itself. Experiments on SimplerEnv demonstrate that the proposed method consistently improves task success rates in both single- and multi-embodiment settings. Further analysis shows that the gains arise primarily from correcting a small number of critical decisions rather than globally altering policy behavior. These results suggest that LPO provides an effective and practical pathway for deployment-time improvement of foundation manipulation policies.