QCircuitNet: A Large-Scale Hierarchical Dataset for Quantum Algorithm Design
Keywords: AI for science, quantum computing, quantum oracle construction, quantum algorithm design
Abstract: Quantum computing is an emerging field recognized for the significant speedup it offers over classical computing through quantum algorithms. However, designing and implementing quantum algorithms pose challenges due to the complex nature of quantum mechanics and the necessity for precise control over quantum states.
Despite the significant advancements in AI, there has been a lack of datasets specifically tailored for this purpose.
In this work, we introduce QCircuitNet, the first benchmark and test dataset designed to evaluate AI's capability in designing and implementing quantum algorithms in the form of quantum circuit codes. Unlike using AI for writing traditional codes, this task is fundamentally different and significantly more complicated due to highly flexible design space and intricate manipulation of qubits.
Our key contributions include:
1. A general framework which formulates the key features of quantum algorithm design task for Large Language Models.
2. Implementation for a wide range of quantum algorithms from basic primitives to advanced applications, with easy extension to more quantum algorithms.
3. Automatic validation and verification functions, allowing for iterative evaluation and interactive reasoning without human inspection.
4. Promising potential as a training dataset through primitive fine-tuning results.
We observed several interesting experimental phenomena: fine-tuning does not always outperform few-shot learning, and LLMs tend to exhibit consistent error patterns. QCircuitNet provides a comprehensive benchmark for AI-driven quantum algorithm design, offering advantages in model evaluation and improvement, while also revealing some limitations of LLMs in this domain.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6802
Loading