AutoQResearch: LLM-Guided Closed-Loop Policy Search for Adaptive Variational Quantum Optimization

TL;DR

AutoQResearch introduces an LLM-guided closed-loop framework for adaptive variational quantum optimization, enabling autonomous discovery of effective solver policies across combinatorial problems.

Contribution

The paper presents a novel LLM-guided policy search framework that adaptively configures variational quantum algorithms for combinatorial optimization tasks.

Findings

Discovered policies outperform static baselines on MIS instances.

CVaR objectives are effective at small scale, QRAO-based qubit compression scales well.

Framework discovers adaptations like sampling budget and hybrid repair protocols for CVRP.

Abstract

Configuring variational quantum algorithms for combinatorial optimization remains a difficult, expert-driven process requiring coordinated choices over solver family, ansatz, objective, and optimizer. We present AutoQResearch, an LLM-guided closed-loop experimentation framework that casts this task as sequential policy search over a curated design space. Instead of a single static configuration, the framework searches for adaptive solver-control policies that condition future decisions on diagnostics such as feasibility, optimality gap, and convergence stagnation. The system operates through a structured workflow: an LLM agent edits a small policy surface under a fixed evaluation harness, candidate policies are screened using cheap scout evaluations, and only the strongest candidates are promoted to full confirmation. This enables controlled autonomous exploration while guarding against proxy overfitting and unstable selection. We evaluate the framework on Maximum Independent Set (MIS) and the Capacitated Vehicle Routing Problem (CVRP). On MIS instances (16--64 vertices), discovered policies substantially outperform static baselines and reveal scale-dependent behavior: CVaR objectives are effective at small scale, while QRAO-based qubit compression provides the most effective explored scaling path. On CVRP curricula (8--12 customers) and a held-out E-n13-k4 benchmark, the framework discovers adaptations involving sampling budget, penalty design, and hybrid repair protocols, yielding high-quality solutions. Methodologically, we find that staged confirmation is essential: cheap proxy evaluations can materially misestimate policy quality and even invert candidate rankings. Overall, the paper positions AutoQResearch as a benchmarked quantum--GenAI co-design workflow for autonomous solver discovery in variational quantum optimization.