让视觉语言动作模型在测试时自动适应环境变化，提升决策可靠性。
Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models
- 通过不确定性的数据增强和动作投票缓解虚假关联问题。
- 在LIBERO上提升7.4%成功率，在Atari上提升10.3%人类基准分数。
- 无需微调基础模型，适合部署在动态环境中的智能体使用。
视觉语言动作模型（VLAs）在序列决策中表现优异，但对环境细微变化（如物体姿态微小改变）仍显脆弱。我们将其归因于轨迹过拟合——模型过度关注动作与实体间的虚假相关性，重复记忆动作模式。为此提出延迟反馈的扰动学习（PDF），一种无需验证器的测试时自适应框架，可在不微调基础模型的前提下提升决策性能。PDF通过基于不确定性的数据增强与动作投票缓解虚假相关性，自适应调度器分配增强预算以平衡效率与效果。为进一步提升稳定性，PDF训练轻量级扰动模块，利用延迟反馈回溯修正动作置信度，解决过自信问题。在LIBERO（+7.4%成功率）和Atari（+10.3%人类归一化得分）上的实验表明，PDF在任务成功率上持续优于基线VLA及测试时自适应模型，为多模态决策智能体提供了实用的可靠测试时自适应路径。代码已公开。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。