SQD-Agent: LLM-driven agentic framework for Quantum Chemistry workflows

2026-09-30

AI Summary

This study addresses the reliance on expert knowledge and high hardware barriers in hybrid quantum chemistry workflows by proposing a large language model (LLM)-driven intelligent framework. Leveraging LLM agent technology, the framework automatically translates natural language intents into executable SQD quantum chemistry workflows. It adopts a modular architecture to enable seamless integration of heterogeneous backends, while incorporating interactive performance profiling and intelligent caching mechanisms to enhance computational efficiency. This work significantly streamlines experimental procedures, facilitating error mitigation strategy analysis and computational resource optimization on real quantum hardware. Ultimately, it provides a low-barrier, highly scalable solution for hybrid quantum-classical computing.

Abstract

Quantum algorithms and quantum hardware are advancing towards a promising paradigm for scientific applications. However, translating domain-specific problems into executable hybrid quantum-classical workflows remains a significant barrier for application researchers due to the required expertise in quantum algorithms, nuances in quantum programming, and hardware-aware system integration. At the same time, AI and primarily LLM based agents are increasingly capable of interpreting natural-language intent, reasoning over complex workflows, and translating high-level objectives into executable code and building computational pipelines. In this work, we introduce SQD Agent, an LLM-based agentic framework that translates natural-language user intent into executable workflows for Quantum Chemistry applications where algorithms from the Sample-Based Quantum Diagonalization (SQD) family are used. By automating this translation, SQD Agent reduces the level of human expertise and configuration overhead required, thereby simplifying experimentation in hybrid quantum-classical settings for application researchers new to quantum. SQD Agent adopts a modular and extensible architecture that supports seamless integration of heterogeneous quantum backends, classical solvers, and workflow components, ensuring adaptability to rapidly evolving quantum ecosystems. The framework further incorporates interactive capabilities for on-demand profiling, bottleneck analysis, resource optimization, intelligent result caching, and convergence visualization. Key features include quantum chemistry experiments, error mitigation on real quantum hardware, together with analysis of candidate mitigation schemes in terms of their potential error-recovery behavior and computational budget, helping users understand their practical trade-offs and decide which strategies to explore in subsequent experiments.

Problem

• Quantum Chemistry
• Hybrid Quantum-Classical Workflows
• LLM-driven Agents
• Workflow Automation

Innovation

• LLM-driven agent
• Quantum Chemistry
• Hybrid quantum-classical workflow
• Sample-Based Quantum Diagonalization
• Error mitigation