A new benchmark evaluates embodied agents in a photorealistic 360-video reconstruction of Akihabara, and state-of-the-art LMM agents score far below local human experts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
A new benchmark evaluates embodied agents in a photorealistic 360-video reconstruction of Akihabara, and state-of-the-art LMM agents score far below local human experts.