Author name: Matin Aghaei, Lingfeng Zhang, Mohammad Ali Alomrani, Mahdi Biparva, Yingxue Zhang

arXiv:2507.20021v3 Announce Type: replace
Abstract: Recent ObjectNav systems credit large language models (LLMs) for sizable zero-shot gains, yet it remains unclear how much comes from language versus geometry. We revisit this question by re-evaluatin…