---
format: "aidr-story-markdown/v1"
id: "0f1cd46063b505b1d026cfe0f24757dadc2b1f904a5117157c8a3c2f40f2f929"
canonical_url: "https://aidr.today/0f1cd460?lang=en"
title: "SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-22T00:00:00.000Z"
category: "Research"
topics: ["agent"]
source_urls: ["https://huggingface.co/papers/2610.26659"]
summary: "SpatialScout is a new benchmark for evaluating vision-language model agents on active object-level 3D mapping, comprising 80 diverse indoor scenes containing 3,140 target objects."
---

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

> [Open the canonical story](<https://aidr.today/0f1cd460?lang=en>)

**Published:** 2026-10-22T00:00:00.000Z
**Category:** Research
**Topics:** agent

## Summary

SpatialScout is a new benchmark for evaluating vision\-language model agents on active object\-level 3D mapping, comprising 80 diverse indoor scenes containing 3,140 target objects\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.26659>)