← Back to all news
arXiv AI By Andi Gu, Alek H. Kemeny, Susanne F. Yelin, Mikhail D. Lukin

Discovering state-of-the-art quantum circuits with large language models

Read the original on arXiv AI →

The paper presents an evolutionary framework where large language models (LLMs) generate quantum circuit designs and an independent evaluator scores them. Applied to tasks in numerical computation, chemistry, optimization, quantum simulation, and number theory, the approach yields circuits that reduce Toffoli and qubit counts in seven of eight tasks, and discovers a new reversible architecture for prime-field modular inversion that improves the Toffoli‑qubit trade‑off. This demonstrates that evaluator‑guided LLM co‑design can produce state‑of‑the‑art quantum algorithms.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 7

LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams

The paper introduces QuantumEvo, an evolutionary framework that employs a large language model (LLM) to generate heuristics for ordering variables in binary decision diagrams (BDDs) used in reversible quantum circuit synthesis. By searching over heuristic families and directly manipulating BDD variable orderings, QuantumEvo produces the HGA-QE heuristic, which modifies the sifting step of a genetic algorithm to better align with quantum circuit cost (QCC). Across benchmark sets, HGA-QE achieves a 70.9% tie-or-win rate against the best per-function baseline and strictly outperforms it on 13.5% of functions, demonstrating competitive QCC performance and a clear advantage on benchmarks from different data sources.

By Yoonju Sim, Federico Berto, Chuanbo Hua, Jinkyoo Park, Changhyun Kwon
llmsbenchmarks
More like this →
arXiv AI
Aug 20

AlphaClifford: Efficient Clifford Synthesis and Transpilation with Model-based RL

AlphaClifford is a model‑based reinforcement learning framework that uses Monte Carlo Tree Search to synthesize Clifford circuits from the H, S, and CNOT gate set. By modeling the state space with the algebraic properties of the symplectic group, it consistently reduces total and two‑qubit gate counts compared to existing heuristics. The approach also extends to hardware‑constrained transpilation and serves as a post‑synthesis optimizer in a full Clifford+T pipeline.

By Daniele Lizzio Bosco, Jacopo Cossio, Carla Piazza, Giuseppe Serra
reinforcement-learningbenchmarks
More like this →
arXiv AI
Aug 14

AutoQuREO: A Framework for Automated Quantum Resource Estimation and Optimization

arXiv:2608. 12936v1 Announce Type: cross Abstract: As quantum computing progresses from proof-of-principle demonstrations toward practical utility, a significant impediment is the need to augment algorithmic feasibility with system-level optimization across heterogeneous hardware and software stacks.

By Harshkumar Oza, Aritra Sarkar, Syed Naqi Abbas, Rahul Bhowmick, Aryan Prakash, Prateek P Kulkarni, Krishna Kumar Sabapathy
More like this →