Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913115273166848 |
|---|---|
| author | Zhao, Jianchao Yang, Huoren Hu, Yusong Gao, Yuyang Ou, Qiguan Wan, Cong Dong, SongLin Ma, Zhiheng Gong, Yihong |
| author_facet | Zhao, Jianchao Yang, Huoren Hu, Yusong Gao, Yuyang Ou, Qiguan Wan, Cong Dong, SongLin Ma, Zhiheng Gong, Yihong |
| contents | Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades under local deployment conditions. Existing evaluations typically treat test episodes as independent zero-shot trials. However, real robots often operate repeatedly in the same or slowly changing environments, where successful executions provide environment-verified evidence of reliable behavior patterns. We study this persistent-deployment setting, asking whether a partially competent frozen VLA can improve its reliability by reusing its successful test-time experience. We propose an online success-memory guided test-time adaptation framework for generative VLAs. During deployment, the robot stores progress-calibrated successful observation-action segments in a long-term memory. At inference, it retrieves state-relevant action chunks, filters inconsistent candidates via trajectory-level consistency, and aggregates them into an elite action prior. To incorporate this prior into action generation, we introduce confidence-adaptive prior guidance, which injects the elite prior into an intermediate state of the flow-matching action sampler and adjusts the guidance strength based on retrieval confidence. This design allows the frozen VLA to exploit environment-specific successful experience while preserving observation-conditioned generative refinement. This retrieve-then-steer mechanism enables lightweight, non-parametric test-time adaptation without requiring parameter updates. Simulation and real-world experiments show improved task success and closed-loop stability, especially in long-horizon and multi-stage tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10094 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs Zhao, Jianchao Yang, Huoren Hu, Yusong Gao, Yuyang Ou, Qiguan Wan, Cong Dong, SongLin Ma, Zhiheng Gong, Yihong Robotics Artificial Intelligence Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades under local deployment conditions. Existing evaluations typically treat test episodes as independent zero-shot trials. However, real robots often operate repeatedly in the same or slowly changing environments, where successful executions provide environment-verified evidence of reliable behavior patterns. We study this persistent-deployment setting, asking whether a partially competent frozen VLA can improve its reliability by reusing its successful test-time experience. We propose an online success-memory guided test-time adaptation framework for generative VLAs. During deployment, the robot stores progress-calibrated successful observation-action segments in a long-term memory. At inference, it retrieves state-relevant action chunks, filters inconsistent candidates via trajectory-level consistency, and aggregates them into an elite action prior. To incorporate this prior into action generation, we introduce confidence-adaptive prior guidance, which injects the elite prior into an intermediate state of the flow-matching action sampler and adjusts the guidance strength based on retrieval confidence. This design allows the frozen VLA to exploit environment-specific successful experience while preserving observation-conditioned generative refinement. This retrieve-then-steer mechanism enables lightweight, non-parametric test-time adaptation without requiring parameter updates. Simulation and real-world experiments show improved task success and closed-loop stability, especially in long-horizon and multi-stage tasks. |
| title | Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.10094 |