Metraipolis › archive › dc_1455d64c767c

MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation — arXiv:2610.00604

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00604
License (as archived)
CC0-1.0
Archived
2026-10-06T12:10:21.478Z
SHA-256 of the archived text
47a2fbbebe9bf8b3a6eb6834d125fc343aeda1a5ba216a18e9fe27db87c167e7
Stable URL of this page
https://metraipolis.com/documento/dc_1455d64c767c

How to cite

MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation — arXiv:2610.00604 — arXiv (en), https://arxiv.org/abs/2610.00604 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1455d64c767c (Metraipolis archive dc_1455d64c767c, sha256 47a2fbbebe9bf8b3a6eb6834d125fc343aeda1a5ba216a18e9fe27db87c167e7)
BibTeX
@misc{dc1455d64c767c,
  title = {MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation — arXiv:2610.00604},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00604},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1455d64c767c; sha256 47a2fbbebe9bf8b3a6eb6834d125fc343aeda1a5ba216a18e9fe27db87c167e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00604. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action policies often see only one or a few recent frames, which makes it difficult to evaluate how they use information that disappears during a task. We introduce MIKASA-Robo-VLA, a benchmark of 90 language-conditioned manipulation tasks. All but 10 hide the cue an action depends on. Those 10 are reactive controls. MIKASA-Robo, the suite it rebuilds, has 32 tasks and uses language only in a representative VLA subset. Here every task provides an instruction, while memory-dependent tasks hide a task-relevant cue and reactive controls keep it available. For 70 tasks, environment phase timings specify an information gap, and for 28 of them the gap exceeds the 16-frame window of the widest fixed-context VLA we survey. The gap counts only the interval the cue is provably absent, not the full duration a policy must retain it, so every memory-dependent task still requires memory by construction, including the ones whose measured gap is short. We release 22,500 oracle trajectories across 10 memory types in RLDS and LeRobotDataset v3. A reference $\pi_{0.5}$ baseline with current images and proprioception, but no observation history or explicit memory module, is fine-tuned on 14 tasks and achieves 0.211 $\pm$ 0.044 mean task success. Its lower success on the evaluated Long-split tasks is confounded by open-loop chunking and the memory types represented in that subset. Project page: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.00604 — 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 2026-10-06T10:21:28.091Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).