Research

Paper

AI LLM March 25, 2026

BRIDG-Q: Barren-Plateau-Resilient Initialisation with Data-Aware LLM-Generated Quantum Circuits

Authors

Ngoc Nhi Nguyen, Thai T Vu, John Le, Hoa Khanh Dam, Dung Hoang Duong, Dinh Thai Hoang

Abstract

Quantum circuit initialisation is a key bottleneck in variational quantum algorithms (VQAs), strongly impacting optimisation stability and convergence. Recent work shows that large language models (LLMs) can synthesise high-quality variational circuit architectures, but their continuous parameter predictions are unreliable. Conversely, data-driven initialisation methods such as BEINIT improve trainability via problem-adaptive priors, yet assume fixed ansatz templates and ignore generative circuit structure. We propose BRIDG-Q (Barren-Plateau-Resilient Initialisation with Data-Aware LLM-Generated Quantum Circuits), a neuro-symbolic pipeline that bridges this gap by coupling LLM-generated circuit architectures with empirical-Bayes parameter initialisation. BRIDG-Q uses AgentQ to generate problem-conditioned circuit topologies, removes generated parameters, and injects data-informed parameter initialisations to mitigate barren plateau effects. Evaluations on graph optimisation benchmarks using residual energy gap and convergence metrics show improved optimisation robustness, indicating that data-driven initialisation remains effective even for LLM-generated circuits, with oracle per-instance selection achieving approximately a 10% reduction in final residual energy.

Metadata

arXiv ID: 2603.23979
Provider: ARXIV
Primary Category: cs.ET
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23979v1</id>\n    <title>BRIDG-Q: Barren-Plateau-Resilient Initialisation with Data-Aware LLM-Generated Quantum Circuits</title>\n    <updated>2026-03-25T06:20:17Z</updated>\n    <link href='https://arxiv.org/abs/2603.23979v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23979v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Quantum circuit initialisation is a key bottleneck in variational quantum algorithms (VQAs), strongly impacting optimisation stability and convergence. Recent work shows that large language models (LLMs) can synthesise high-quality variational circuit architectures, but their continuous parameter predictions are unreliable. Conversely, data-driven initialisation methods such as BEINIT improve trainability via problem-adaptive priors, yet assume fixed ansatz templates and ignore generative circuit structure. We propose BRIDG-Q (Barren-Plateau-Resilient Initialisation with Data-Aware LLM-Generated Quantum Circuits), a neuro-symbolic pipeline that bridges this gap by coupling LLM-generated circuit architectures with empirical-Bayes parameter initialisation. BRIDG-Q uses AgentQ to generate problem-conditioned circuit topologies, removes generated parameters, and injects data-informed parameter initialisations to mitigate barren plateau effects. Evaluations on graph optimisation benchmarks using residual energy gap and convergence metrics show improved optimisation robustness, indicating that data-driven initialisation remains effective even for LLM-generated circuits, with oracle per-instance selection achieving approximately a 10% reduction in final residual energy.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.ET'/>\n    <published>2026-03-25T06:20:17Z</published>\n    <arxiv:comment>14 pages, 2 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.ET'/>\n    <author>\n      <name>Ngoc Nhi Nguyen</name>\n    </author>\n    <author>\n      <name>Thai T Vu</name>\n    </author>\n    <author>\n      <name>John Le</name>\n    </author>\n    <author>\n      <name>Hoa Khanh Dam</name>\n    </author>\n    <author>\n      <name>Dung Hoang Duong</name>\n    </author>\n    <author>\n      <name>Dinh Thai Hoang</name>\n    </author>\n  </entry>"
}