QuantumMatterExplorer: An Autonomous Agent for the Discovery of Quantum Many-Body Phases of Matter
Abstract
Mapping the phase diagram of a new quantum Hamiltonian demands expert judgement at every step: which observables to measure, where in parameter space to compute, or how to separate genuine order from finite-size artefacts. We introduce QuantumMatterExplorer, an autonomous agent that takes only a Hamiltonian and its parameter ranges as input and returns a phase diagram obtained from its own numerical simulations. The agent is built on a large language model and is designed to reason over a long horizon, maintain a persistent written plan, and drive a set of computational tools, with density-matrix renormalization group (DMRG) calculations cross-checked against independent exact diagonalization. The agent combines a large language model with persistent planning, a library of expert computational-physics skills, and density-matrix renormalization group calculations validated against independent exact diagonalization. It adaptively selects quantities to evaluate, refines parameter scans, and performs finite-size analyses as evidence accumulates. After validating the approach on Hamiltonians with known transitions, we challenge it with a frustrated bilinear-biquadratic spin-1 chain with single-ion anisotropy, whose two-dimensional phase diagram was published only recently and is unlikely to appear in any training corpus. Given no hint about the expected physics, the agent proposes which observables to probe, and identifies candidate Néel, Haldane and dimerized phases, in broad agreement with the reference phase diagram. It also detects incommensurate correlations and infers the frustration-dependent geometry of the phase boundaries, all within an eight-hour compute budget. These results open a practical route to the autonomous computational discovery of new phases of quantum matter.
Related
- Soft Contrastive Learning for Unsupervised Discovery of Phases of Matter
- Lifting the mixed to the pure: quantum phases of matter from canonical purification
- Thermal robustness of sensing quantum phases of matter via qubit probes
- TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
- Designing Strongly Correlated Quantum Phases of Matter with Foundation Neural-Network Quantum States
BibTeX
@misc{nys2026quantummatterexplorer,
title = {{QuantumMatterExplorer: An Autonomous Agent for the Discovery of Quantum Many-Body Phases of Matter}},
author = {Jannes Nys and Andrew Jreissaty and Juan Carrasquilla},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32001},
eprint = {2610.32001},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32001},
}
RIS
TY - UNPB
TI - QuantumMatterExplorer: An Autonomous Agent for the Discovery of Quantum Many-Body Phases of Matter
AU - Jannes Nys
AU - Andrew Jreissaty
AU - Juan Carrasquilla
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2610.32001
UR - https://arxiv.org/abs/2610.32001
AB - Mapping the phase diagram of a new quantum Hamiltonian demands expert judgement at every step: which observables to measure, where in parameter space to compute, or how to separate genuine order from finite-size artefacts. We introduce QuantumMatterExplorer, an autonomous agent that takes only a Hamiltonian and its parameter ranges as input and returns a phase diagram obtained from its own numerical simulations. The agent is built on a large language model and is designed to reason over a long horizon, maintain a persistent written plan, and drive a set of computational tools, with density-matrix renormalization group (DMRG) calculations cross-checked against independent exact diagonalization. The agent combines a large language model with persistent planning, a library of expert computational-physics skills, and density-matrix renormalization group calculations validated against independent exact diagonalization. It adaptively selects quantities to evaluate, refines parameter scans, and performs finite-size analyses as evidence accumulates. After validating the approach on Hamiltonians with known transitions, we challenge it with a frustrated bilinear-biquadratic spin-1 chain with single-ion anisotropy, whose two-dimensional phase diagram was published only recently and is unlikely to appear in any training corpus. Given no hint about the expected physics, the agent proposes which observables to probe, and identifies candidate Néel, Haldane and dimerized phases, in broad agreement with the reference phase diagram. It also detects incommensurate correlations and infers the frustration-dependent geometry of the phase boundaries, all within an eight-hour compute budget. These results open a practical route to the autonomous computational discovery of new phases of quantum matter.
ER -