Newest papers

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

Zhaoxi Zhang, Hao Liang, Linxuan Wu, Yiming Wu, Yifu Yuan, Kun Liang, Chenming Tang, Meiyi Qiang · 2026 · arXiv

DOI: 10.48550/arXiv.2610.26659 · open-access PDF

Spanish

La inteligencia espacial requiere que los agentes adquieren activamente evidencias visuales e integren las observaciones en una representación coherente del mundo tridimensional. Sin embargo, la respuesta a las preguntas espaciales ofrece una evidencia limitada de si los modelos pueden construir mapas métricos precisos a través de la exploración autónoma. Introducimos SpatialScout, un benchmark para evaluar los agentes del modelo de lenguaje visual (VLM) en el mapeo 3D a nivel de objeto activo. SpatialScout incluye 80 escenas interiores diversas que contienen 3.140 objetos objetivo. Dado un inventario de objetos, observaciones RGB, calibración de cámara y posturas de cámara, los agentes co

Machine translation (Meta M2M100); the English original follows.

Abstract

Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spatial question answering offers limited evidence of whether models can construct accurate metric maps through autonomous exploration. We introduce SpatialScout, a benchmark for evaluating vision-language model (VLM) agents on active object-level 3D mapping. SpatialScout comprises 80 diverse indoor scenes containing 3,140 target objects. Given an object inventory, RGB observations, camera calibration, and camera poses, agents co

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26659, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange