Jul 2026
SceneActBench: Can Agents Act on the 3D Scenes They See?
This work presents SceneActBench, a benchmark for visually conditioned action across five 3D tasks under a unified agent-environment loop, and evaluates each final output against hidden ground truth with task-specific geometric metrics.
Yifei Zhao, Xiangxin Zhou, Wenhao Yang et al.
· arXiv.org · 2 citations