Metraipolis › archive › dc_8a03f8a91b99

AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents — arXiv:2609.28973

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28973
License (as archived)
CC0-1.0
Archived
2026-10-08T07:16:36.855Z
SHA-256 of the archived text
7b744608ccb6fd6ae79517e16e621a1e51cadc5ef2712224ced9e2de8390e9cf
Stable URL of this page
https://metraipolis.com/documento/dc_8a03f8a91b99

How to cite

AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents — arXiv:2609.28973 — arXiv (en), https://arxiv.org/abs/2609.28973 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a03f8a91b99 (Metraipolis archive dc_8a03f8a91b99, sha256 7b744608ccb6fd6ae79517e16e621a1e51cadc5ef2712224ced9e2de8390e9cf)
BibTeX
@misc{dc8a03f8a91b99,
  title = {AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents — arXiv:2609.28973},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28973},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a03f8a91b99; sha256 7b744608ccb6fd6ae79517e16e621a1e51cadc5ef2712224ced9e2de8390e9cf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28973. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physical changes or sensing errors can invalidate embodied agents' task-relevant beliefs. AquaMend compares re-probing, rollback, and supported continuation on a probe-belief-action graph under an expected-loss objective covering sensing, physical recovery, and uncorrected failures. A joint posterior guides a one-step policy with conditional detection-power screening. The per-belief three-way optimum requires independence, separability, and fully resolving probes; the general policy has no global optimality guarantee. Across 32 paired scenarios in a self-constructed simulation benchmark, AquaMend recovers in 28/32 cases and reduces mean complete loss by 21.6% versus restart. Its paired loss difference from decision-theoretic troubleshooting (DTT) is not statistically significant after Holm correction. Against the all-candidate ablation, online decision time decreases by 12.3% overall but increases by 3.4% in the uncovered late stage.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.28973 — 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 2026-10-08T06:38:53.762Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).