We present CAFES, a correlation-aware agentic framework for electronic-structure simulations of strongly correlated systems. CAFES addresses two challenges: the fragmented software landscape for many-body calculations and the difficulty of selecting appropriate methods across diverse correlation regimes. It combines correlation diagnostics, adaptive method selection, and large language model (LLM) assistance for molecular, crystalline, and model-Hamiltonian systems. A study-task architecture separates study-level planning from task-level execution, while a curated scientific knowledge layer provides reusable guidance for method selection, workflow design, and result interpretation. We demonstrate CAFES through three research-level studies: calculating the low-lying electronic states of lutein using DMRG-CASSCF, probing phase competition in the extended honeycomb Hubbard model using DMET, and generating a quantum-chemical dataset with CCSD labels. These calculations demonstrate the potential of agentic workflows for strongly correlated electronic-structure problems, a regime that has received limited attention in existing agentic computational frameworks.
We present CAFES, a correlation-aware agentic framework for electronic-structure simulations of strongly correlated systems. CAFES addresses two challenges: the fragmented software landscape for many-body calculations and the difficulty of selecting appropriate methods across diverse correlation regimes. It combines correlation diagnostics, adaptive method selection, and large language model (LLM) assistance for molecular, crystalline, and model-Hamiltonian systems. A study-task architecture separates study-level planning from task-level execution, while a curated scientific knowledge layer provides reusable guidance for method selection, workflow design, and result interpretation. We demonstrate CAFES through three research-level studies: calculating the low-lying electronic states of lutein using DMRG-CASSCF, probing phase competition in the extended honeycomb Hubbard model using DMET, and generating a quantum-chemical dataset with CCSD labels. These calculations demonstrate the potential of agentic workflows for strongly correlated electronic-structure problems, a regime that has received limited attention in existing agentic computational frameworks.
Progress towards quantum utility in chemistry requires not only algorithmic advances, but also the identification of chemically meaningful problems whose electronic structure fundamentally challenges classical methods. Here, we introduce a curated hierarchy of chemically decisive benchmark systems designed to probe distinct regimes of electronic correlation relevant to molecular, bioinorganic, and heavy-element chemistry. Moving beyond minimal toy models, our benchmark set spans multireference bond breaking (N2), high-spin transition-metal chemistry (FeS), biologically relevant iron-sulfur clusters ([2Fe-2S]), and actinide-actinide bonding (U2), which exhibits extreme sensitivity to active-space choice, relativistic treatment, and correlation hierarchy even within advanced multireference frameworks. As a concrete realization, we benchmark a recently developed automated and adaptive quantum algorithm based on generator-coordinate-inspired subspace expansion,ADAPT-GCIM, using a black-box workflow that integrates entropy-based active-space selection via the ActiveSpaceFinder tool. Across this chemically diverse problem set, ADAPT-GCIM achieves high accuracy in challenging correlation regimes. Equally importantly, these benchmarks expose general failure modes and design constraints-independent of any specific algorithm-highlighting the necessity of problem-aware and correlation-specific strategies for treating strongly correlated chemistry on quantum computers. To support systematic benchmarking and reproducible comparisons, the Hamiltonians for all systems studied are made openly available.
Achieving materials-specific predictions for large, realistic molecules and solids with strong electron correlations remains a long-standing challenge in quantum chemistry. This dissertation develops scalable ab initio quantum many-body methods for crystalline materials, demonstrating that rigorous optimization of theoretical approximations and numerical algorithms enables predictive computation even in strongly correlated systems. The work tackles three interconnected challenges, namely describing material-specific properties of strongly correlated superconductors, achieving linear scaling with k-points for large-scale periodic calculations, and establishing reliable methods for electron-phonon interactions. The following chapters address each challenge in turn. Chapter 2 demonstrates that ab initio density matrix embedding theory, combined with symmetry-breaking strategies for superconducting order parameters, reproduces experimental trends in cuprate superconductivity, including pressure and layer effects on transition temperatures. By directly solving the electronic Schrödinger equation from material structures, these calculations capture multi-orbital covalency effects that simplified model Hamiltonians neglect, revealing their essential role in the spin fluctuations driving pairing. This predictive capability establishes a foundation for efficient computational screening of superconducting materials. Extending these calculations to larger k-point meshes and broader phase diagram explorations, however, demands more efficient computational algorithms. To overcome this computational bottleneck, Chapter 3 introduces interpolative separable density fitting framework. This development enables thermodynamic limit calculations with up to 1000 k-points, as validated on diamond, carbon dioxide, nickel monoxide, and cuprate systems. Integration with density matrix embedding theory and local natural orbital methods further yields converged ground-state energies from accurate correlated wavefunction methods such as CCSD(T) for crystalline materials in the thermodynamic limit. With computational efficiency established, the remaining challenge lies in extending the theoretical framework beyond purely electronic degrees of freedom. Chapter 4 addresses this need by establishing exponential ansatz wavefunctions as competitive approaches for electron-phonon systems. Unlike previous treatments based on perturbation theory, systematic benchmarking of coupled cluster theory and variational Lang-Firsov methods on the Holstein model demonstrates, for the first time, that these approaches accurately describe polaron formation across coupling regimes when combined with appropriate reference state optimization. These results provide a foundation for incorporating phonon effects into ab initio studies of superconducting materials. In addition to these methodological advances, GPU acceleration and MPI parallelization enhance computational throughput, enabling efficient large-scale calculations. Together, these developments constitute a computational framework for predictive ab initio quantum many-body calculations in crystalline materials, opening new avenues for understanding and designing strongly correlated quantum materials.
Fully automated self-driving laboratories promise high-throughput, large-scale scientific discovery by reducing repetitive labor. However, they require deep integration of laboratory knowledge, which is often unstructured, multimodal, and hard to incorporate into current AI systems. This paper introduces the "k-agents" framework, designed to support experimentalists in organizing laboratory knowledge and automating experiments with agents. The framework uses large-language-model-based agents to encapsulate laboratory knowledge, including available operations and methods for analyzing results. To automate experiments, execution agents break multistep procedures into agent-based state machines, interact with other agents to execute steps, and analyze results. These results drive state transitions, enabling closed-loop feedback control. We demonstrate the system on a superconducting quantum processor, where agents autonomously planned and executed experiments for hours, successfully producing and characterizing entangled quantum states at human-level performance. Our knowledge-based agent system opens new possibilities for managing laboratory knowledge and accelerating scientific discovery.
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.
Quantum simulation is central to understanding and designing quantum systems across physics and chemistry. Yet it has barriers to access from both computational complexity and computational perspectives, due to the exponential growth of Hilbert space and the complexity of modern software tools. Here we introduce{\cinzel El Agente Cuántico}, a multi-agent AI system that automates quantum-simulation workflows by translating natural-language scientific intent into executed and validated computations across heterogeneous quantum-software frameworks. By reasoning directly over library documentation and APIs, our agentic system dynamically assembles end-to-end simulations spanning state preparation, closed- and open-system dynamics, tensor-network methods, quantum control, quantum error correction, and quantum resource estimation. The developed system unifies traditionally distinct simulation paradigms behind a single natural-language interface. Beyond reducing technical barriers, this approach opens a path toward scalable, adaptive, and increasingly autonomous quantum simulation, enabling faster exploration of physical models, rapid hypothesis testing, and closer integration between theory, simulation, and emerging quantum hardware.
A central obstacle in realizing color center cavity-QED-based quantum technologies is inhomogeneity, or disorder, among individual emitters. As the number of emitters increases, so does the complexity of the experimental data, making it difficult to quantify the present physical mechanisms of disorder. Here we introduce an artificial intelligence-driven model discovery framework in which a large language model (LLM)-based agent, equipped with tools and a structured workflow, proposes candidate Hamiltonian and Lindbladian models, generates computational tools, and quantitatively evaluates competing physical hypotheses. We apply the workflow to three previously published experimental cavity-QED datasets collected from color centers in diamond and silicon carbide. Across the experiments, the agent successfully identifies physical models for the system and characterizes the disorder. In assessing reproducibility, we find that run-to-run variability is concentrated primarily in the research plan generation step, while the computational analysis itself is substantially more consistent. Our results suggest that structured LLM agent workflows can support model discovery from quantum optical experimental data while simultaneously allowing for human expert supervision and collaboration.