Metraipolis › archive › dc_bd5e2a097173
TaskAnchor: Grounding Task State in Reactive VLAs for Long-Horizon Manipulation — arXiv:2609.23580
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23580
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:24:01.395Z
- SHA-256 of the archived text
a862df35d4e8fdced00efb28f9ef9ddf686677c54c0bed65c9d17ff727776687- Stable URL of this page
https://metraipolis.com/documento/dc_bd5e2a097173
How to cite
TaskAnchor: Grounding Task State in Reactive VLAs for Long-Horizon Manipulation — arXiv:2609.23580 — arXiv (en), https://arxiv.org/abs/2609.23580 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd5e2a097173 (Metraipolis archive dc_bd5e2a097173, sha256 a862df35d4e8fdced00efb28f9ef9ddf686677c54c0bed65c9d17ff727776687)
BibTeX
@misc{dcbd5e2a097173,
title = {TaskAnchor: Grounding Task State in Reactive VLAs for Long-Horizon Manipulation — arXiv:2609.23580},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23580},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd5e2a097173; sha256 a862df35d4e8fdced00efb28f9ef9ddf686677c54c0bed65c9d17ff727776687},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23580. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reactive vision-language-action (VLA) policies suffer from task-state aliasing in long-horizon manipulation, where identical multimodal inputs call for distinct, context-dependent actions. Given that pretrained VLAs already possess rich control primitives to express diverse behaviors, we hypothesize that the execution bottleneck lies not in policy capacity, but in input ambiguity. In this paper, we propose TaskAnchor, a lightweight adapter that grounds task state by injecting execution context into the VLA's native input space. During post-training, TaskAnchor learns to represent the semantic execution stage as a milestone-supervised coordinate prepended to the language instruction, while incorporating fine-grained historical evidence via a residual update to the current visual tokens. This formulation avoids generating complex subtask instructions and leaves the backbone architecture unchanged. Across long-horizon benchmarks, TaskAnchor delivers substantial gains, achieving approximately 6 times the average success rate of the pi0.5 and X-VLA baselines on RMBench and more than doubling the task success rate of pi0.5 on RoboMemArena. Real-robot experiments further validate reliable multi-stage execution, with the same policy adapting its subsequent behaviors using earlier human interactions as in-context cues. Our project website is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.23580 — 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 2026-10-09T21:59:59.605Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).