AI Agents for Quantum Computing
Giving language-model agents the ability to actually run and design quantum programs, not just write code that looks plausible.
Most work on AI for science stops at generating code. The harder problem is execution: a quantum workload has to be compiled, scheduled across QPUs and HPC clusters, and run asynchronously on remote hardware before anyone learns whether the idea was any good.
My QCNC 2026 paper closes part of that gap with a Model Context Protocol server for quantum execution, letting an agent invoke sampling and expectation-value primitives directly against the ABCI-Q hybrid platform and remote hardware. The MITOU Target project extends the same idea from execution to design — an agent platform that assembles quantum circuits itself.
LLM agents · Model Context Protocol · CUDA-Q · OpenQASM · quantum-HPC

