# Generative Thermal Design Through Boundary Representation and Multi-Agent Cooperative Environment

arXiv: https://arxiv.org/abs/2208.07952 · HTML: https://mlsanity.com/paper/2208.07952/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 16 Aug 2022.

## Builds on (most cited first, 8 of 8)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [Vitruvion: A Generative Model of Parametric CAD Sketches](https://mlsanity.com/paper/2109.14124/) (2021)
- [Neural reparameterization improves structural optimization](https://mlsanity.com/paper/1909.04240/) (2019)
- [Geodesic Convolutional Shape Optimization](https://mlsanity.com/paper/1802.04016/) (2018)
- [Modeling 3D Shapes by Reinforcement Learning](https://mlsanity.com/paper/2003.12397/) (2020)
- [MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization](https://mlsanity.com/paper/2009.07110/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Reward-Directed Diffusion Framework for Generative Design Optimization](https://mlsanity.com/paper/2508.01509/) (2025)
- [HeatGen: A Guided Diffusion Framework for Multiphysics Heat Sink Design Optimization](https://mlsanity.com/paper/2511.09578/) (2025)

## Abstract (arXiv)

Generative design has been growing across the design community as a viable method for design space exploration. Thermal design is more complex than mechanical or aerodynamic design because of the additional convection-diffusion equation and its pertinent boundary interaction. We present a generative thermal design using cooperative multi-agent deep reinforcement learning and continuous geometric representation of the fluid and solid domain. The proposed framework consists of a pre-trained neural network surrogate model as an environment to predict heat transfer and pressure drop of the generated geometries. The design space is parameterized by composite Bezier curve to solve multiple fin shape optimization. We show that our multi-agent framework can learn the policy for design strategy using multi-objective reward without the need for shape derivation or differentiable objective function.