Zhaoxi Zhang, Hao Liang, Linxuan Wu, Yiming Wu, Yifu Yuan, Kun Liang, Chenming Tang, Meiyi Qiang, Wentao Zhang, Weikang Li · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26659 · cited by 0 works (OpenAlex) · open-access PDF
अंतरिक्ष सक्रिय बुद्धि के माध्यम से भरोसा करने के लिए एजेंटों को सक्रिय रूप से दृश्य सबूत प्राप्त करने और दृश्य-भाषा मॉडल (VLM) एजेंटों का मूल्यांकन करने के लिए एक समग्र प्रतिनिधित्व में निगरानी को एकीकृत करने की आवश्यकता है। हालांकि अंतरिक्ष प्रश्न जवाब देने के लिए सीमित सबूत प्रदान करता है कि क्या मॉडल स्वचालित सर्वेक्षण के माध्यम से सटीक मीट्रिक नक्शे का निर्माण कर सकते हैं। हम SpatialScout, एक दृश्य-भाषा मॉडल (VLM) एजेंटों का मूल्यांकन करने के लिए एक बेंचमार्क की पेशकश करते हैं। SpatialScout 80 विविध आंतरिक दृश्यों को शामिल करता है जिसमें 3,140 लक्षित वस्तुएं हैं। एक वस्तु
Machine translation (Meta M2M100); the English original follows.
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 control a camera to explore each scene and estimate object centers in a shared coordinate frame. The task requires coordinating viewpoint selection, cross-view association, geometric estimation, and map revision under bounded interaction budgets. Evaluation jointly measures localization accuracy and target coverage through object-scale overlap scores that penalize missing predictions. Experiments with frontier VLMs reveal substantial limitations: the strongest evaluated model, Claude Opus 5.5, achieves a mean overlap score of 41.71%, with 47.23% of targets exceeding an intersection-over-union (IoU) threshold of 0.5 and only 3.25% exceeding 0.9. These results reveal a substantial gap between recovering coarse object layouts and constructing complete, precise metric maps. SpatialScout provides a quantitative testbed for developing agents that build reliable 3D spatial representations through active perception. Code is available at https://github.com/JesseZZZZZ/SpatialScout.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Artificial intelligence, Computer science, Object (grammar), Testbed, Representation (politics), Computer vision
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange