ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2606.25800v1
• Date: Wed, 24 Jun 2026 13:17:59 GMT
• Title: ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models
• Abstract summary: We propose an advantage-guided self-distillation framework that constructs a teacher directly in action space by perturbing action-token logits with calibrated advantage estimates.<n>Across seven robotic manipulation environments with in-distribution and out-of-distribution shifts, ROADVLA outperforms PPO in nearly all settings.
• Score: 11.1063401404824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action policies. Although self-distillation can in principle provide denser training signals, we find that text-based privileged teachers conditioned on demonstrations, retrieved experiences, or high-level plans are ineffective for VLA adaptation, exposing a modality gap between symbolic guidance and low-level robot actions. We propose ROAD-VLA, an advantage-guided self-distillation framework that constructs a proximal teacher directly in action space by perturbing action-token logits with calibrated advantage estimates. This converts sparse rewards into dense token-level supervision while keeping the teacher close to the current policy. We further derive a policy-improvement lower bound under calibrated advantages and accurate teacher matching. Across seven robotic manipulation environments with in-distribution and out-of-distribution shifts, ROADVLA outperforms PPO in nearly all settings, demonstrating robust online VLA adaptation.

Related papers

• RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation [19.642319972162255]
  We present RA-VLA, a retrieval-augmented VLA framework that integrates behavior-aligned context retrieval with a grounded execution pipeline.<n> RA-VLA achieves superior success rates and computational efficiency, establishing a robust framework for training-free robotic adaptation.
  arXiv  Detail & Related papers  (2026-08-26T09:52:30Z)
• Latent On-Policy Self-Distillation [55.57800223145407]
  On-policy self-distillation (OPSD) offers an effective pathway by using a privileged self-teacher to provide dense supervision on the student's own trajectories.<n>Existing methods still rely heavily on designer-specified privileged artifacts.<n>We introduce Latent On-Policy Self-Distillation (LOPD), which makes the teacher's privileged context itself learnable end-to-end from experience.
  arXiv  Detail & Related papers  (2026-08-13T10:05:51Z)
• Semi-Supervised Vision-Language-Action Model [17.893249958828218]
  Vision-Language-Action (VLA) models enable robots to predict actions directly from visual observations and language instructions, but adapting them to new environments still depends on costly action-labeled demonstrations.<n>We study semi-supervised VLA adaptation under limited supervision signals, where only a small portion of trajectories contain robot actions and the remaining trajectories provide action-unlabeled vision-language observations.<n>Unlike standard semi-supervised learning, the missing supervision is an embodied action signal that must be visually grounded, language-consistent, physically feasible, and temporally stable.
  arXiv  Detail & Related papers  (2026-06-19T14:42:52Z)
• Teacher-Guided Policy Optimization for LLM Distillation [90.49982387646861]
  Teacher-Guided Policy Optimization (TGPO) is an on-policy algorithm that incorporates dense directional guidance by leveraging teacher predictions conditioned on the student's rollout.<n>Experiments on complex reasoning benchmarks demonstrate that TGPO significantly outperforms standard baselines and is robust to different teachers.
  arXiv  Detail & Related papers  (2026-05-13T09:20:03Z)
• 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-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation [14.33516456804297]
  On-Policy VLA Distillation (VLA-OPD) is a framework bridging the efficiency of online Reinforcement Learning (RL) with the robustness of offline Supervised Fine-Tuning (SFT)
  arXiv  Detail & Related papers  (2026-03-27T17:59:33Z)
• 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)
• 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)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation [67.98620973023709]
  VOLD is a framework to transfer reasoning capabilities from text-only teacher models to VLM student models.<n>We show that VOLD outperforms the baseline model significantly and improves over the state of the art by a margin.
  arXiv  Detail & Related papers  (2025-10-27T16:32:12Z)
• IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction [51.130510883952546]
  Vision-Language-Action (VLA) models leverage pretrained vision-language models (VLMs) to couple perception with robotic control.<n>We propose textbfIntentionVLA, a VLA framework with a curriculum training paradigm and an efficient inference mechanism.<n>Our proposed method first leverages carefully designed reasoning data that combine intention inference, spatial grounding, and compact embodied reasoning.
  arXiv  Detail & Related papers  (2025-10-09T04:49:46Z)

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.