Metraipolis › archive › dc_a403cfdd3651
Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models — arXiv:2608.24042
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24042
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:41.583Z
- SHA-256 of the archived text
1ae5f8181ea9de2c5d5dc0cfe77ff5bd7bc8f9976c6fc079fe076073e8e81a4a- Stable URL of this page
https://metraipolis.com/documento/dc_a403cfdd3651
How to cite
Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models — arXiv:2608.24042 — arXiv (en), https://arxiv.org/abs/2608.24042 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a403cfdd3651 (Metraipolis archive dc_a403cfdd3651, sha256 1ae5f8181ea9de2c5d5dc0cfe77ff5bd7bc8f9976c6fc079fe076073e8e81a4a)
BibTeX
@misc{dca403cfdd3651,
title = {Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models — arXiv:2608.24042},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24042},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a403cfdd3651; sha256 1ae5f8181ea9de2c5d5dc0cfe77ff5bd7bc8f9976c6fc079fe076073e8e81a4a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24042. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While Vision-Language-Action (VLA) models pretrained on large-scale robot datasets provide a strong foundation for robot manipulation, their performance can degrade when adapted to new tasks with limited task-specific demonstrations. Retrieval offers a practical way to reuse existing demonstrations for data-efficient adaptation, but existing methods often rely on visual similarity, state-action representations, or task-level language matching. These approaches may overlook the hierarchical structure of long-horizon manipulation tasks, where complete task matches are rare but reusable skills are often abundant. To address this challenge, we propose Hierarchical Skill Retrieval (HSR), a retrieval framework for data-efficient VLA adaptation. Specifically, HSR first decomposes a target task into candidate skill sequences. It evaluates each plan based on both semantic plausibility and skill reliability estimated from the prior dataset. The selected decomposition is then used for hybrid retrieval. This combines subtask-level language retrieval with behavior-feature reranking to identify demonstrations that are both semantically relevant and compatible with the target task. Finally, we adapt the policy through a two-stage pretraining and finetuning pipeline, which separates general skill acquisition from task-specific adaptation. Experiments on the LIBERO benchmark and several real-world robot manipulation tasks show that HSR improves the average success rate by 10.3% and 21.3% over the strongest baseline, respectively. These results demonstrate the effectiveness of structured skill-level retrieval for data-efficient VLA adaptation. Videos and code are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.24042 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T06:28:52.334Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).