AI for Circuit Synthesis,
Optimization, and Discovery 

Workshop Overview

Summary
The objective of this workshop is to facilitate dissemination and exchange between scholars and practitioners on how Artificial Intelligence (AI) can be leveraged to address some fundamental tasks of gate-based quantum computing: Circuit Synthesis, Circuit Optimization, and Circuit Discovery. 

Abstract
Quantum Computing is steadily increasing in capabilities and scale, promising transformative breakthroughs in fields ranging from materials science to cryptography.  However, realizing this potential—especially on near-term hardware and early fault-tolerant architectures—requires overcoming severe physical limitations. A key  challenge is the efficient compilation of high-level quantum algorithms into executable physical instructions. To maximize the utility of available qubits and coherence times, quantum circuits must be  synthesized,  optimized, and sometimes discovered entirely from scratch. Traditional heuristic and rule-based methods often struggle to scale or fail to identify optimal configurations within the exponentially large and complex design space of quantum circuits.

This workshop explores Artificial Intelligence (AI) as a powerful solution to these bottlenecks. We specifically focus on the deployment of Deep Learning (DL) and Reinforcement Learning (RL) techniques, which have demonstrated a unique capability to navigate vast, high-dimensional search spaces efficiently. Because RL agents and neural networks excel at pattern recognition and reward-based exploration, they are uniquely equipped to synthesize complex unitaries into native gate sets, to aggressively reduce circuit depth to mitigate noise, and to discover entirely novel quantum circuit ansatzes.

By bringing together scholars and practitioners from both the AI and Quantum Computing communities, this workshop will highlight state-of-the-art AI-driven compilation strategies. We aim to facilitate a cross-disciplinary exchange to address current training limitations, share recent breakthroughs, and chart the future course of AI in accelerating the path toward practical quantum advantage.

Call for papers
We invite research submissions exploring the synergy between Artificial Intelligence and Quantum Circuit design. We specifically seek contributions making use of Deep Learning and Reinforcement Learning to address circuit synthesis, hardware-aware optimization, and automated ansatz discovery. The application of AI-based approaches in circuit synthesis, optimization, and discovery is key to overcoming physical limitations of current devices and moving towards the practical "quantum utility" era. 

For more information, see our Call for papers page.

Contacts