analiza aiqbench
The paper uses AI agents in an iterative improve-and-evaluate loop, with a frozen exact verifier checking every result, to tune quantum simulation compilation problems. It reports reductions of up to 73% in the optimized cost at the largest sizes, beating published constructions and a state-of-the-art optimizer on fermion-to-qubit encodings. For readers, the key points are the verification design, which makes results auditable, and the method's reliance on problems whose solutions can be checked efficiently. The gains are measured on compilation cost in simulation, not yet shown to translate into end-to-end performance on real hardware.
Automating quantum circuit optimization with AI agents
arXiv:2610.31352v1 Announce Type: new Abstract: Compiling quantum algorithms for real devices involves hard optimization problems that can decide whether an algorithm runs at scale. We present a general method for solving such problems with AI agents, with every result certified. It builds on autoresearch loops, in which agents iteratively improve programs against a fixed evaluator and which have recently improved quantum cryptanalysis circuits, and adds two elements: a frozen, exact verifier certifies every result, and this verifier, together with the challenge around it, is built by an agent that formulates the problem with a researcher and validates the verifier against a solved case, deliberately broken solutions and published results before any solution exists. The method applies to any optimization problem whose solutions can be verified exactly and efficiently. We apply it to three compilation problems in quantum simulation, namely fermion-to-qubit encoding, Hamiltonian layout and unitary synthesis. In each, the agents improved substantially on published or standard constructions, reducing the cost being optimized by up to 73% at the largest sizes tested and outperforming a state-of-the-art optimizer for fermion-to-qubit encodings. Every submission is a program accompanied by its agent's notes, so the ideas behind each improvement are recorded in human-readable form; later agents built on them, and we describe them here. These results open the way to automated, certified discovery across quantum circuit design and beyond.
Abstract:Compiling quantum algorithms for real devices involves hard optimization problems that can decide whether an algorithm runs at scale. We present a general method for solving such problems with AI agents, with every result certified. It builds on autoresearch loops, in which agents iteratively improve programs against a fixed evaluator and which have recently improved quantum cryptanalysis circuits, and adds two elements: a frozen, exact verifier certifies every result, and this verifier, together with the challenge around it, is built by an agent that formulates the problem with a researcher and validates the verifier against a solved case, deliberately broken solutions and published results before any solution exists. The method applies to any optimization problem whose solutions can be verified exactly and efficiently. We apply it to three compilation problems in quantum simulation, namely fermion-to-qubit encoding, Hamiltonian layout and unitary synthesis. In each, the agents improved substantially on published or standard constructions, reducing the cost being optimized by up to 73% at the largest sizes tested and outperforming a state-of-the-art optimizer for fermion-to-qubit encodings. Every submission is a program accompanied by its agent's notes, so the ideas behind each improvement are recorded in human-readable form; later agents built on them, and we describe them here. These results open the way to automated, certified discovery across quantum circuit design and beyond.
arXiv:2610.31352 [quant-ph]
(or arXiv:2610.31352v1 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2610.31352 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 311 cuvinte
Subiecte conexe
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
arXiv · 2 oct. 2026
Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations
arXiv · 18 aug. 2026
Optimize blueprint extraction accuracy in Amazon Bedrock Data Automation
AWS · 11 iun. 2026
OptScientist: Automated Discovery of Optimization Laws
arXiv · 21 oct. 2026