# A multi-agentic framework for real-time, autonomous freeform metasurface design

arXiv: https://arxiv.org/abs/2503.20479 · HTML: https://mlsanity.com/paper/2503.20479/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 107 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Fourier Neural Operator with Learned Deformations for PDEs on General Geometries](https://mlsanity.com/paper/2207.05209/) (2022)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow](https://mlsanity.com/paper/2109.03697/) (2021)
- [Physics-informed neural networks with hard constraints for inverse design](https://mlsanity.com/paper/2102.04626/) (2021)
- [hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition](https://mlsanity.com/paper/2003.05385/) (2020)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs](https://mlsanity.com/paper/1909.10145/) (2019)
- [Deep neural networks for the evaluation and design of photonic devices](https://mlsanity.com/paper/2007.00084/) (2020)
- [AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligence](https://mlsanity.com/paper/2407.10022/) (2024)
- [Global optimization of dielectric metasurfaces using a physics-driven neural network](https://mlsanity.com/paper/1906.04157/) (2019)
- [OptoGPT: A Foundation Model for Inverse Design in Optical Multilayer Thin Film Structures](https://mlsanity.com/paper/2304.10294/) (2023)
- [PreAct: Prediction Enhances Agent's Planning Ability](https://mlsanity.com/paper/2402.11534/) (2024)
- [Towards General Neural Surrogate Solvers with Specialized Neural Accelerators](https://mlsanity.com/paper/2405.02351/) (2024)

## Built on by (most cited first, 14 of 14)

- [An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design](https://mlsanity.com/paper/2506.06935/) (2025)
- [Inverse Design in Nanophotonics via Representation Learning](https://mlsanity.com/paper/2507.00546/) (2025)
- [ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms](https://mlsanity.com/paper/2512.03476/) (2025)
- [GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation](https://mlsanity.com/paper/2602.15039/) (2026)
- [Accurate and scalable deep Maxwell solvers using multilevel iterative methods](https://mlsanity.com/paper/2509.03622/) (2025)
- [Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces](https://mlsanity.com/paper/2509.24196/) (2025)
- [A Self-Evolving Agentic Framework for Metasurface Inverse Design](https://mlsanity.com/paper/2604.01480/) (2026)
- [SelfAI: A self-directed framework for long-horizon scientific discovery](https://mlsanity.com/paper/2512.00403/) (2025)
- [Research and Prototyping Study of an LLM-Based Chatbot for Electromagnetic Simulations](https://mlsanity.com/paper/2511.17680/) (2025)
- [A Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization](https://mlsanity.com/paper/2605.15418/) (2026)
- [Agentic Root Cause Analysis through Evidence-Grounded Reasoning](https://mlsanity.com/paper/2607.22385/) (2026)
- [VortexChat: An agentic framework for autonomous multi-objective integrated photonic design](https://mlsanity.com/paper/2608.20688/) (2026)
- [Towards a universal meta-optics solver via large language models](https://mlsanity.com/paper/2608.26417/) (2026)
- [HALO: A Physics-Aware LLM Agent Framework for Nanophotonic Design](https://mlsanity.com/paper/2608.28877/) (2026)

## Abstract (arXiv)

Innovation in nanophotonics currently relies on human experts who synergize specialized knowledge in photonics and coding with simulation and optimization algorithms, entailing design cycles that are time-consuming, computationally demanding, and frequently suboptimal. We introduce MetaChat, a multi-agentic design framework that can translate semantically described photonic design goals into high-performance, freeform device layouts in an automated, nearly real-time manner. Multi-step reasoning is enabled by our Agentic Iterative Monologue (AIM) paradigm, which coherently interfaces agents with code-based tools, other specialized agents, and human designers. Design acceleration is facilitated by Feature-wise Linear Modulation-conditioned Maxwell surrogate solvers that support the generalized evaluation of metasurface structures. We use freeform dielectric metasurfaces as a model system and demonstrate with MetaChat the design of multi-objective, multi-wavelength metasurfaces orders of magnitude faster than conventional methods. These concepts present a scientific computing blueprint for utilizing specialist design agents, surrogate solvers, and human interactions to drive multi-physics innovation and discovery.