# PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding

arXiv: https://arxiv.org/abs/2603.22796 · HTML: https://mlsanity.com/paper/2603.22796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM](https://mlsanity.com/paper/2312.02126/) (2023)
- [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025)
- [HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment](https://mlsanity.com/paper/2503.23907/) (2025)
- [Multimodal LLMs Can Reason about Aesthetics in Zero-Shot](https://mlsanity.com/paper/2501.09012/) (2025)
- [AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning](https://mlsanity.com/paper/2109.09923/) (2021)
- [PhotoBot: Reference-Guided Interactive Photography via Natural Language](https://mlsanity.com/paper/2401.11061/) (2024)
- [Learning to Take Good Pictures of People with a Robot Photographer](https://mlsanity.com/paper/1904.05688/) (2019)
- [LeRoP: A Learning-Based Modular Robot Photography Framework](https://mlsanity.com/paper/1911.12470/) (2019)

## Abstract (arXiv)

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.