Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2604.18107v1
• Date: Mon, 20 Apr 2026 11:25:51 GMT
• Title: Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models
• Abstract summary: Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts.<n>We propose Perturbation learning with Delayed Feedback (PDF), a verifier-free test-time adaptation framework.
• Score: 48.89466384943165
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, such as small changes in object pose. We attribute this brittleness to trajectory overfitting, where VLAs over-attend to the spurious correlation between actions and entities, then reproduce memorized action patterns. We propose Perturbation learning with Delayed Feedback (PDF), a verifier-free test-time adaptation framework that improves decision performance without fine-tuning the base model. PDF mitigates the spurious correlation through uncertainty-based data augmentation and action voting, while an adaptive scheduler allocates augmentation budgets to balance performance and efficiency. To further improve stability, PDF learns a lightweight perturbation module that retrospectively adjusts action logits guided by delayed feedback, correcting overconfidence issue. Experiments on LIBERO (+7.4\% success rate) and Atari (+10.3 human normalized score) demonstrate consistent gains of PDF in task success over vanilla VLA and VLA with test-time adaptation, establishing a practical path toward reliable test-time adaptation in multimodal decision-making agents. The code is available at \href{https://github.com/zhoujiahuan1991/CVPR2026-PDF}{https://github.com/zhoujiahuan1991/CVPR2026-PDF}.

Related papers

• AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models [1.0323063834827415]
  We propose AdaVLA, an online, training-free adaptive framework for fast yet accurate flow-matching-based Vision-Language-Action models.<n>We show that our method achieves $1.87times$ and $2.24times$ speedups for $_0.5$ and X-VLA, respectively, with negligible degradation in success rates.
  arXiv  Detail & Related papers  (2026-08-29T11:44:18Z)
• Uncertainty Quantification for Flow-Based Vision-Language-Action Models [33.28454469934064]
  Vision-language-action models (VLAs) combine vision-language backbones with expressive generative action heads trained via flow matching on large-scale robotic datasets.<n>Despite their strong empirical performance in robotic manipulation, VLAs lack mechanisms to quantify confidence in their predictions and to detect when their actions may be unreliable.<n>We propose SAVE, a framework for uncertainty-guided active fine-tuning that reduces the number of costly expert demonstrations required to adapt VLAs to new tasks.
  arXiv  Detail & Related papers  (2026-06-16T15:19:09Z)
• Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models [32.87104367896446]
  We propose an end-to-end framework that leverages failure trajectories as adaptive negative guidance for diffusion- and flow-based VLA policies.<n>AFIL uses a pretrained VLA to generate failure rollouts online, avoiding the need for handcrafted failure-mode design.<n>It then jointly trains Dual Action Generators (DAGs) for successful and failed behaviors while sharing a common vision-language backbone.
  arXiv  Detail & Related papers  (2026-05-08T19:57:11Z)
• VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model [54.35791816657227]
  We introduce textbfVLA-ATTC', a framework that endows VLA models with adaptive test-time compute.<n>VLA-ATTC employs an uncertainty-based cognitive clutch'' to dynamically transition from reflexive execution to a TTC deliberation phase.<n>On the LIBERO-LONG benchmark, VLA-ATTC reduces the failure rate of the SOTA model PI0.5 by over 50%.
  arXiv  Detail & Related papers  (2026-05-02T02:13:11Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding [60.06899554269808]
  CycleVLA is a system that equips Vision-Language-Action models (VLAs) with proactive self-correction.<n>CycleVLA achieves this by integrating a progress-aware VLA that flags critical subtask transition points.<n>Extensive experiments show that CycleVLA improves performance for both well-trained and under-trained VLAs.
  arXiv  Detail & Related papers  (2026-01-05T17:31:01Z)
• 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)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models [28.422082187079166]
  We introduce RoboMonkey, a test-time scaling framework for Vision-Language-Action (VLA) models.<n>RoboMonkey samples a small set of actions from a VLA, applies Gaussian perturbation and majority voting to construct an action proposal distribution, and then uses a Vision Language Model (VLM)-based verifier to select the optimal action.<n>We show that pairing existing VLAs with RoboMonkey yields significant performance gains, achieving a 25% absolute improvement on out-of-distribution tasks and 9% on in-distribution tasks.
  arXiv  Detail & Related papers  (2025-06-21T20:56:17Z)
• Debiased Prompt Tuning in Vision-Language Model without Annotations [14.811475313694041]
  Vision-Language Models (VLMs) may suffer from the problem of spurious correlations.<n>By leveraging pseudo-spurious attribute annotations, we propose a method to automatically adjust the training weights of different groups.<n>Our approach efficiently improves the worst-group accuracy on CelebA, Waterbirds, and MetaShift datasets.
  arXiv  Detail & Related papers  (2025-03-11T12:24:54Z)
• Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation [67.18144414660681]
  We propose a Fast-Slow Test-Time Adaptation (FSTTA) approach for online Vision-and-Language Navigation (VLN) Our method obtains impressive performance gains on four popular benchmarks.
  arXiv  Detail & Related papers  (2023-11-22T07:47:39Z)

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.