Metraipolis › archive › dc_f778b1fa498c
Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration? — arXiv:2610.34149
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34149
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:12:40.410Z
- SHA-256 of the archived text
45b5eb1f0d80baa7bd5132ef3bfb050630ef3f6e00189939e7376cf30ef4c1bf- Stable URL of this page
https://metraipolis.com/documento/dc_f778b1fa498c
How to cite
Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration? — arXiv:2610.34149 — arXiv (en), https://arxiv.org/abs/2610.34149 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f778b1fa498c (Metraipolis archive dc_f778b1fa498c, sha256 45b5eb1f0d80baa7bd5132ef3bfb050630ef3f6e00189939e7376cf30ef4c1bf)
BibTeX
@misc{dcf778b1fa498c,
title = {Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration? — arXiv:2610.34149},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34149},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f778b1fa498c; sha256 45b5eb1f0d80baa7bd5132ef3bfb050630ef3f6e00189939e7376cf30ef4c1bf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34149. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While Multimodal Large Language Models (MLLMs) excel at zero-shot reasoning, their spatial capabilities are primarily evaluated through static, passive observation. In complex, human-centric scenes, occlusion often hides crucial geometric evidence, and passive benchmarks force models to guess rather than recognize their own visual uncertainty. To bridge this gap, we introduce SATE-Bench, a novel interactive benchmark comprising 316 real-world scenes and 2,525 multi-turn QA pairs to evaluate visual self-awareness and active exocentric view-exploration. It combines a Passive multi-view control with an Active exploration setting, where models start from a severely occluded view and must iteratively query adjacent viewpoints until they gather enough evidence to fully ``sate'' the question, scored by a step-penalized efficiency reward. Evaluating state-of-the-art MLLMs reveals that they terminate exploration prematurely while reporting high confidence, and struggle with fine-grained 3D geometric tasks; matched-view controls further attribute the Active--Passive gap primarily to insufficient evidence acquisition. Moreover, fine-tuning with Group Relative Policy Optimization (GRPO) shows that rewarding view-seeking increases active exploration but lowers overall accuracy, as models over-explore and fail to fuse expanding multi-view contexts across turns. These findings indicate that scaling passive multi-view perception does not intrinsically yield active spatial reasoning, highlighting the need for models that know where to look, how to integrate what they see, and when to stop. Code and data are available at this https URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.34149 — 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 2026-10-27T07:56:00.301Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).