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

TL;DR

BRIDG-Q introduces a neuro-symbolic approach combining LLM-generated quantum circuit architectures with data-informed parameter initialisation to improve variational quantum algorithm performance and robustness against barren plateaus.

Contribution

It presents a novel pipeline that couples LLM-generated circuit structures with empirical-Bayes initialisation, enhancing trainability and convergence in variational quantum algorithms.

Findings

Achieves approximately 10% reduction in residual energy on benchmarks.

Improves optimisation robustness with data-driven initialisation.

Demonstrates effectiveness of LLM-generated circuits with proper initialisation.

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.