Metraipolis › archive › dc_93f8ae80fca0
Answering Without Arriving: An Evidence Audit for Embodied Question Answering — arXiv:2611.01958
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01958
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:43:42.868Z
- SHA-256 of the archived text
c8775231ce8de061eda50bb6f2cade17e7fb3b86895d8fe933cd195d92a13dc9- Stable URL of this page
https://metraipolis.com/documento/dc_93f8ae80fca0
How to cite
Answering Without Arriving: An Evidence Audit for Embodied Question Answering — arXiv:2611.01958 — arXiv (en), https://arxiv.org/abs/2611.01958 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_93f8ae80fca0 (Metraipolis archive dc_93f8ae80fca0, sha256 c8775231ce8de061eda50bb6f2cade17e7fb3b86895d8fe933cd195d92a13dc9)
BibTeX
@misc{dc93f8ae80fca0,
title = {Answering Without Arriving: An Evidence Audit for Embodied Question Answering — arXiv:2611.01958},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01958},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_93f8ae80fca0; sha256 c8775231ce8de061eda50bb6f2cade17e7fb3b86895d8fe933cd195d92a13dc9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01958. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Embodied question answering asks an agent to navigate, observe, and then answer questions about what it saw, yet answer accuracy alone cannot tell whether any of this happened. A plausible answer can come from the question, the room label, or the answer choices, and a correct answer does not show that the supporting observation was ever made. We present a multi-room benchmark whose 200 test episodes and 800 questions are stratified by route extent, with an evaluation ladder that holds the questions fixed while varying only the evidence supplied to the answerer, from text-only probes through closed-loop agents to replay of the reference trajectory. Questions are generated from symbolic records of rooms, visible objects, and frames, so every answer can be traced to the observations that support it. A closed-loop vision-language agent reaches no target in 200 episodes yet answers 45.5% of questions, within 0.1 points of the same model given no images; replaying the reference trajectory raises the same model to 57.4%, so the evidence exists along the route but is not gathered. A family-level audit then shows that access to evidence is not the same as use of it. Four of eight families are largely answerable from text, one cites frames that cannot establish its own answer, and the oracle conditions reach 59.5% on Rooms-visited by counting the supplied images. Evidence acquisition, answer coverage, and shortcut sensitivity must therefore be established before an accuracy gain can be credited to memory. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.01958 — 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 2026-11-03T11:06:37.686Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).