Metraipolis › archive › dc_3940322f2a36

Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents — arXiv:2610.00282

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00282
License (as archived)
CC0-1.0
Archived
2026-10-06T12:01:41.412Z
SHA-256 of the archived text
fae9285293b5e3182fae11a89ce9e2a793ce99647b8c0d6805321bb2f8d4795e
Stable URL of this page
https://metraipolis.com/documento/dc_3940322f2a36

How to cite

Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents — arXiv:2610.00282 — arXiv (en), https://arxiv.org/abs/2610.00282 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3940322f2a36 (Metraipolis archive dc_3940322f2a36, sha256 fae9285293b5e3182fae11a89ce9e2a793ce99647b8c0d6805321bb2f8d4795e)
BibTeX
@misc{dc3940322f2a36,
  title = {Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents — arXiv:2610.00282},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00282},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3940322f2a36; sha256 fae9285293b5e3182fae11a89ce9e2a793ce99647b8c0d6805321bb2f8d4795e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00282. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting, rejecting, inspecting the world, and asking the speaker. GAVA implements this interface with observation-bounded evidence, legal probes, and a one-step expected-loss rule. In text-only ALFWorld, 162 checkpoints produce 972 paired true and false interventions. Complete local inspections give GAVA and always verify 100 percent correction accuracy, establishing the evidence contract rather than a comparative advantage. In same-episode execution, GAVA reduces interaction cost against always verify but ties a cost threshold under a perfect speaker. An exploratory training-only object-location prior lowers interaction and declared joint cost on 340 unseen scenarios by 0.490 and 0.420 relative to uniform GAVA. After freezing the policy, costs, baselines, and multiplicity plan, the gains replicate on 77 non-overlapping seen checkpoints, covering 308 scenarios: 0.595 and 0.517, with both 95 percent checkpoint-bootstrap confidence intervals excluding zero. Joint cost also improves over an identical-prior fixed policy, while the matched calibrated no-VOI comparison remains inconclusive. Semantic GAVA makes four factual errors in each cohort, corresponding to 98.8 percent and 98.7 percent accuracy, and all methods complete every task. Results support selective information gathering with semantic priors under declared costs, but do not establish a general advantage of environmental value of information over clarification. The study uses normalized claims, complete symbolic observations, and controlled speakers; it evaluates neither human participants, visual input, nor physical robots.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.00282 — 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 2026-10-06T10:21:27.853Z 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).