# Scalable Quantum State Preparation via Large-Language-Model-Driven Discovery

arXiv: https://arxiv.org/abs/2505.06347 · HTML: https://mlsanity.com/paper/2505.06347/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 26 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 3 of 3)

- [Variational Quantum Algorithms](https://mlsanity.com/paper/2012.09265/) (2020)
- [Barren plateaus in quantum neural network training landscapes](https://mlsanity.com/paper/1803.11173/) (2018)
- [Quantum Architecture Search: A Survey](https://mlsanity.com/paper/2406.06210/) (2024)

## Built on by (most cited first, 5 of 5)

- [Detailed balance in large language model-driven agents](https://mlsanity.com/paper/2512.10047/) (2025)
- [Iterated Agent for Symbolic Regression](https://mlsanity.com/paper/2510.08317/) (2025)
- [Practical Quantum CIM Empowerment via All-Domestic-Core Agentic Large Model](https://mlsanity.com/paper/2605.23934/) (2026)
- [Where to Search: Measure the Prior-Structured Search Space of LLM Agents](https://mlsanity.com/paper/2510.14846/) (2025)
- [Fine-Tuning Large Language Models for Quantum Reasoning](https://mlsanity.com/paper/2606.21974/) (2026)

## Abstract (arXiv)

Efficient quantum state preparation remains a central challenge in first-principles quantum simulations of dynamics in quantum field theories, where the Hilbert space is intrinsically infinite-dimensional. Here, we introduce a large language model (LLM)-assisted framework for quantum-circuit design that systematically scales state-preparation circuits to large lattice volumes. Applied to a 1+1d XY spin chain, the LLM autonomously discovers a compact 4-parameter circuit that captures boundary-induced symmetry breaking with sub-percent energy deviation, enabling successful validation on the textttZuchongzhi quantum processor. Guided by this insight, we extend the framework to 2+1d quantum field theories, where scalable variational ans"atze have remained elusive. For a scalar field theory, the search yields a symmetry-preserving, 3-parameter shallow-depth ansatz whose optimized parameters converge to size-independent constants for lattices n ≥ 4, providing, to our knowledge, the first scalable ansatz for this class of 2+1d models. Our results establish a practical route toward AI-assisted, human-guided discovery in quantum simulation.