Reproduce “Discovering state-of-the-art quantum circuits with large language models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Andi Gu, Alek H. Kemeny, Susanne F. Yelin, Mikhail D. Lukin
The authors present evaluator-guided LLM search for redesigning algorithms and reversible cleanup in quantum circuits. It evaluates candidates by Toffoli and peak-qubit costs. The Reed–Solomon decoder uses 440,000 Toffolis and 1,837 peak qubits, versus 5.1 million and 1,938 for its prior baseline. Across eight tasks, costs improve in seven; modular inversion yields a divsteps architecture without a reported prior-baseline comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.