# Phythesis: Physics-Guided Evolutionary Scene Synthesis for Energy-Efficient Data Center Design via LLMs

arXiv: https://arxiv.org/abs/2512.10611 · HTML: https://mlsanity.com/paper/2512.10611/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 37 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs](https://mlsanity.com/paper/2312.00093/) (2023)
- [LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery](https://mlsanity.com/paper/2405.09783/) (2024)
- [Human-centric Indoor Scene Synthesis Using Stochastic Grammar](https://mlsanity.com/paper/1808.08473/) (2018)
- [Penetrative AI: Making LLMs Comprehend the Physical World](https://mlsanity.com/paper/2310.09605/) (2023)
- [Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency](https://mlsanity.com/paper/2309.17382/) (2023)
- [LLMR: Real-time Prompting of Interactive Worlds using Large Language Models](https://mlsanity.com/paper/2309.12276/) (2023)
- [Automatically Learning Hybrid Digital Twins of Dynamical Systems](https://mlsanity.com/paper/2410.23691/) (2024)
- [SceneGenAgent: Precise Industrial Scene Generation with Coding Agent](https://mlsanity.com/paper/2410.21909/) (2024)
- [MOSAIC: A Multi-Objective Optimization Framework for Sustainable Datacenter Management](https://mlsanity.com/paper/2311.08583/) (2023)
- [Transforming Future Data Center Operations and Management via Physical AI](https://mlsanity.com/paper/2504.04982/) (2025)
- [A Water Efficiency Dataset for African Data Centers](https://mlsanity.com/paper/2412.03716/) (2024)

## Abstract (arXiv)

Data center (DC) infrastructure serves as the backbone to support the escalating demand for computing capacity. Traditional design methodologies that blend human expertise with specialized simulation tools scale poorly with the increasing system complexity. Recent studies adopt generative artificial intelligence to design plausible human-centric indoor layouts. However, they do not consider the underlying physics, making them unsuitable for the DC design that sets quantifiable operational objectives and strict physical constraints. To bridge the gap, we propose Phythesis, a novel framework that synergizes large language models (LLMs) and physics-guided evolutionary optimization to automate simulation-ready (SimReady) scene synthesis for energy-efficient DC design. Phythesis employs an iterative bi-level optimization architecture, where (i) the LLM-driven optimization level generates physically plausible three-dimensional layouts and self-criticizes them to refine the scene topology, and (ii) the physics-informed optimization level identifies the optimal asset parameters and selects the best asset combination. Experiments on three generation scales show that Phythesis achieves 57.3% generation success rate increase and 11.5% power usage effectiveness (PUE) improvement, compared with the vanilla LLM-based solution.