Embodied agents for creative tasks like photography must bridge the semantic gap between high-level language commands and geometric control. We introduce PhotoAgent, an agent that achieves this by integrating Large Multimodal Models (LMMs) reasoning with a novel control paradigm. PhotoAgent first translates subjective aesthetic goals into solvable geometric constraints via LMM-driven, chain-of-thought (CoT) reasoning, allowing an analytical solver to compute a high-quality initial viewpoint. This initial pose is then iteratively refined through visual reflection within a photorealistic internal world model built with 3D Gaussian Splatting (3DGS). This ``mental simulation'' replaces costly and slow physical trial-and-error, enabling rapid convergence to aesthetically superior results. Evaluations confirm that PhotoAgent excels in spatial reasoning and achieves superior final image quality.
@article{arxiv.2603.22796,
title = {PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding},
author = {Lirong Che and Zhenfeng Gan and Yanbo Chen and Junbo Tan and Xueqian Wang},
journal= {arXiv preprint arXiv:2603.22796},
year = {2026}
}
Comments
Accepted to the IEEE International Conference on Robotics and Automation (ICRA) 2026