cs.LGOct 1, 2026

The AI Theorist reveals excitonic structure in αα-RuCl3_3

Authors: Hongjian Zhou, Xianfan Nie, Sean Wu, Tarun Patel, Jinge Wu, Andrew Liu, Adam Wei Tsen, David A. Clifton

Organizations: University of Oxford, Oxford, United Kingdom · University of Waterloo, Waterloo, Canada · Stanford University, Stanford, USA · University College London, London, United Kingdom

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Advances in experimental instrumentation and automation generate increasingly rich datasets, but turning experimental observations into microscopic understanding remains a bottleneck in scientific discovery. To accelerate this process, we introduce AI Theorist, a system of artificial intelligence (AI) agents for autonomous discovery of physical models through hypothesis generation, first-principles calculations and evidence-driven refinement. We apply the framework to αα-RuCl3_3, a leading candidate material for realizing a Kitaev quantum spin liquid, to investigate its electronic structure through optical spectra. AI Theorist develops a new interpretation of the optical and photocurrent observations, identifying distinct excitonic states with contrasting optical selection rules and real-space distributions. To our knowledge, this is the first demonstration of an AI system autonomously developing a physical model to explain previously unpublished experimental observations in a quantum material, utilizing first-principles electronic-structure and many-body calculations. Our results establish a route to autonomous theoretical discovery in materials science, in which AI agents use first-principles calculations to turn experimental observations into physical models and testable predictions.

Figures & tables

Figure 1: Architecture and workflow of AI Theorist. a, Human scientists set the overall research direction, plan experiments with AI Theorist and perform the measurements. Drawing on the resulting observations and prior knowledge, AI Theorist autonomously develops physical models through iterative hypothesis generation, calculation design, execution and critique. Robot badges denote agent roles. b, AI Theorist assists with measurement, instrument and protocol selection. Scientists finalize the protocols and perform measurements, providing new evidence for the computational investigation. c, The α\alpha -RuCl 3 investigation proceeds from the broad aim of understanding electronic excitations in a correlated quantum material, through AI-assisted experimental design and measurements, to autonomous model development. Reflection and photocurrent spectra serve as complementary probes of electronic excitations. AI Theorist formulates and tests hypotheses, including the role of spin–orbit coupling, using DFT– GWGW –Bethe–Salpeter calculations. Candidate interpretations address excitonic character, spin–orbit effects and optical selection rules.
Figure 2: Crystal structure, device geometry and optical response of α\alpha -RuCl 3 . a, Atomic structure and schematic RuCl 3 vertical junction device under illumination. The upper and lower graphene electrodes are contacted from opposite sides; atomic radii and device dimensions are illustrative. b, Photocurrent spectrum; inset shows reflection contrast, dR/RdR/R , over 0.75–1.50 eV. Labels identify the experimental LL , α\alpha , α′\alpha^{\prime} and β\beta features. c, Zigzag, armchair and in-plane-averaged spectra from the electronic-structure and excitonic calculations: GWGW -IP (SOC), GWGW –BSE (no SOC) and GWGW –BSE (SOC). The SOC spectra use 64-point calculations; the no-SOC reference uses 36 points and is not a matched-grid SOC control. Each calculation uses one normalization factor, the maximum in-plane average over 0.6–2.65 eV, shared across its three traces; Gaussian broadening is 0.08 eV. The displayed window is 0.6–2.3 eV; energies are unshifted and no additional smoothing is applied. Experimental photocurrent, reflection contrast and calculated dielectric response are distinct observables.
Figure 3: Electronic structure and conditional exciton distributions. a, DFT+ UU +SOC bands for the 64-point spinor calculation, quasiparticle bands in the fixed two-branch GWGW scissors representation used for the optical calculation, and Ru/Cl projected density of states. The path Γ\Gamma –F–M– Γ\Gamma –Z–Q–M contains 109 sampled points and 168 spinor bands. Each band panel uses its own valence-band maximum as zero; the indirect gaps along this path are 0.811 and 1.770 eV. The GWGW curves apply the near-gap linear corrections to the mean-field bands; they are not an explicit momentum-dependent self-energy calculation along the path. The projected DOS uses 16-point orbital projections at the corrected energies and Gaussian broadening of 0.10 eV. b, Conditional electron distributions for the 64-point SOC LL , α\alpha and α′\alpha^{\prime} candidates and a representative β\beta -region state, evaluated relative to a fixed hole position. All maps use the same electron–hole spinor component (1,1)(1,1) and the commensurate 8×4×28\times 4\times 2 periodic box. Densities are summed along the third lattice-grid direction and plotted on hole-relative in-plane coordinates; white crosses mark the fixed hole. Each map is normalized to its own maximum, with a shared logarithmic colour scale from 10−410^{-4} to 1. The comparison shows spatial distributions rather than relative integrated weights.
Figure 4: From experimental observations to a candidate physical interpretation. Human scientists supply reflection and photocurrent spectra together with sample context. AI Theorist hypothesizes roles for spin–orbit coupling and Coulomb screening, designs separate tests of their effects on the band structure, and evaluates optical consequences using GW–BSE calculations. Critique addresses causal isolation, spectral discrepancies and the relation between calculated and measured observables; these checks guide model refinement and proposed polarization and screening tests.
More in this topic

Autonomous Scientific Discovery

Autonomous scientific discovery develops AI systems that generate, test, and refine scientific hypotheses using data, computation, and experiments.

See all 128 papers

Explore similar work

CardsList

  1. From Data to Theory: Autonomous Large Language Model Agents for Materials Science

    Apr 1, 2026Samuel Onimpa Alfred, Veera SundararaghavanLarge Language Model-Guided Scientific DiscoveryScientific Discovery

    Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI 48109

  2. Qumus: Realization of An Embodied AI Quantum Material Experimentalist

    May 18, 2026Lihan Shi, Zhaoyi Joy Zheng, Xinzhe Juan +14AI Agents for Scientific DiscoveryMaterials Science

    Department of Physics, Princeton University, Princeton, New Jersey 08544, USA · Department of Electrical and Computer Engineering, Princeton University, Princeton, New Jersey 08544, USA · Department of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan 48109, USA +5

  3. Crystal-structure design by agentic AI in a language of motifs

    Aug 16, 2026Dinh-Khiet Le, Minh-Quyet Ha, Hong-Phuc Vu-Dinh +6Crystal Structure GenerationMaterials Discovery

    Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa 923-1292, Japan · Department of Physics, School of Science, Institute of Science Tokyo, 2-12-1 Ookayama, Meguro-ku, Tokyo 152-8551, Japan · Research Center for Materials Informatics, Department of Advanced Data Science, The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa, Tokyo 190-8562, Japan +1