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

• URL: http://arxiv.org/abs/2606.03127v1
• Date: Tue, 02 Jun 2026 04:10:39 GMT
• Title: TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models
• Abstract summary: Vision-Language-Action (VLA) models have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time.<n>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.<n>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?<n>We address this question with TTT-VLA, a test-time training framework based on Latent Prompt Optimization (LPO)
• Score: 49.463896453707065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction [8.801486222527984]
  Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams.<n>We introduce a reliable TTT framework for VLA policies (VANE)<n>On SimplerEnv WidowX, VANE improves average success by $3.2$ percentage points over the corresponding TTT baseline.
  arXiv  Detail & Related papers  (2026-08-10T11:22:54Z)
• Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training [52.78248352851176]
  Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models.<n>We study this residual axis as task learnability: a regime-conditional measure of expected positive response to continued training.<n>We propose TrajVal, a lightweight probe-based estimator that approximates per-task learnability from a short probe run and two endpoint evaluations.
  arXiv  Detail & Related papers  (2026-08-10T07:43:05Z)
• SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning [38.54413500261524]
  Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions.<n>We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills.
  arXiv  Detail & Related papers  (2026-07-16T09:57:18Z)
• Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies [48.31565681022125]
  Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time.<n>We argue that optimal adaptation policies should be learned from task environments, not hand-engineered based on human intuition.<n>We introduce Meta-TTL, a framework that formulates the discovery of effective adaptation policies as a bi-level optimization problem.
  arXiv  Detail & Related papers  (2026-04-01T12:41:01Z)
• 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)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Agentic Policy Optimization via Instruction-Policy Co-Evolution [44.74237684380034]
  INSPO is a novel framework for instruction-policy co-evolution.<n>It integrates instruction optimization as a dynamic component of the reinforcement learning loop.<n>In experiments, INSPO achieves substantial performance gains with only a marginal increase in computational overhead.
  arXiv  Detail & Related papers  (2025-12-01T17:56:29Z)
• Test-time Offline Reinforcement Learning on Goal-related Experience [50.94457794664909]
  Research in foundation models has shown that performance can be substantially improved through test-time training.<n>We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state.<n>Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out.
  arXiv  Detail & Related papers  (2025-07-24T21:11:39Z)
• TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization [12.061547251822326]
  Trajectory-based Group Relative Policy Optimization (TGRPO) is an online RL-based training framework for Visual-Language-Action (VLA) models.<n>We show that TGRPO achieves an average success rate of 80.7%, which is 4.2% higher than that of Supervised Fine-Tuning (SFT) and outperforms other representative RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-06-10T04:27:49Z)

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.