Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimization
Published in IEEE International Conference on Quantum Computing and Engineering (QCE), 2025
We describe Agent-Q, an LLM fine-tuning system to generate and optimize quantum circuits. Agent-Q provides 14,000 quantum circuits covering 12 optimization problem instances and their optimized QAOA, VQE, and adaptive VQE circuits. Experimental results show superior performance of Agent-Q, compared to several state-of-the-art LLMs. Presented at IEEE QCE 2025.