# Weight-Space Programming of Variational Quantum Circuits: Large Language Models Write Quantum Circuit Parameters Without an Optimizer

DevFeed: [Weight-Space Programming of Variational Quantum Circuits: Large Language Models Write Quantum Circuit Parameters Without an Optimizer](<https://devfeed.tech/articles/weight-space-programming-of-variational-quantum-circuits-large-language-models-write-quantum-circuit-parameters-without-an-optimizer-126133.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11537>)

Author: Debarshi Kundu, Swaroop Ghosh, Vasant G Honavar

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [programming](<https://devfeed.tech/tags/programming.md>), [quant-ph](<https://devfeed.tech/tags/quant-ph.md>), [quantum-circuits](<https://devfeed.tech/tags/quantum-circuits.md>), [weight-space-programming](<https://devfeed.tech/tags/weight-space-programming.md>)

## AI overview

The study finds that an LLM can write useful variational circuit angles without optimizer feedback when the parameters have interpretable structure. Across 139 requests, it reached 95-100% of the energy spectrum on the tested VQE problems, produced the exact H₂ ground state in closed form, found optimal depth-one QAOA angles for every tested graph, and achieved 93-96% accuracy on digits 3 versus 8 using 12-18 hand-written weights. Those weights also gave optimizers strong warm starts, reaching their best value after a median of one evaluation instead of hundreds. With permission to design circuits, the LLM encoded pixel importance in data-dependent rotation chains and achieved 65% accuracy across ten digits. Results weaken in opaque weight spaces: fixed circuits with more than 30 weights fell to chance accuracy while optimization improved. Gate conventions also mattered; 6 of 42 QAOA replies reversed mixing-angle signs and failed.

## Source excerpt

arXiv:2611.11537v1 Announce Type: cross Abstract: Variational quantum algorithms (VQAs) optimize circuit angles through repeated quantum-device evaluations, often facing vanishing gradients and high optimization costs. We ask whether a large language model (LLM) can write these angles directly. Extending *weight-space programming* from classical networks to quantum circuits, we provide a frontier LLM (\gpt) with the problem, circuit, and gate conventions. Its angles are executed exactly as written, without returning losses, gradients, or accuracy feedback. Across 139 requests, we test handwritten-digit classification, VQE ground-state estimation for spin chains and H$_2$, and MaxCut QAOA, comparing against random weights, classical optimization, and optimization initialized with LLM weights on the same circuit. When parameters have interpretable structure, the LLM matches or approaches the optimizer: it achieves 95--100\% of the energy spectrum on every VQE problem, derives the exact H$_2$ ground state in closed form, finds optimal depth-one QAOA angles for every graph, and reaches 93--96\% accuracy on digits 3 versus 8 with 12--18 hand-written weights, outperforming an optimizer trained on the same ten examples. Its weights are also strong warm starts: optimization reaches its best value after a median of one evaluation rather than hundreds. Allowed to design circuits, the LLM chooses data-dependent rotation chains encoding pixel importance in all 30 cases (one qubit for binary tasks, one chain per qubit for ten classes), reaching 65\% accuracy across ten digits. Yet the approach fails in opaque weight spaces: accuracy drops to chance when fixed circuits exceed 30 weights, while optimization improves. It is also sensitive to gate conventions: 6 of 42 QAOA replies reverse mixing-angle signs and fail. We release all prompts, replies, and scores.