The AI Theorist reveals excitonic structure in $α$-RuCl$_3$

2026-10-01

AI Summary

This study addresses the bottleneck in scientific discovery where experimental observations are difficult to translate into microscopic physical models by developing a multi-agent collaborative AI system. This system establishes a closed loop integrating hypothesis generation, first-principles electronic structure calculations, and evidence-driven optimization. For the first time, it enables AI to autonomously construct physical models that explain unpublished experimental data of quantum materials. Specifically, this work successfully reveals excitonic states with distinct selection rules in α-RuCl₃, establishing an autonomous pathway from raw data to theoretical discovery. By demonstrating that AI can independently derive physically meaningful models directly from experimental measurements, this research provides a novel paradigm for AI-driven scientific discovery in condensed matter physics.

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 $α$-RuCl$_3$, 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this is the first demonstration of an AI system autonomously developing a physical model to explain previously unpublished experimental observations in a quantum material, utilizing first-principles electronic-structure and many-body calculations.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.

Problem

• alpha-RuCl3
• excitonic structure
• optical spectra
• electronic structure
• quantum spin liquid

Innovation

• AI Theorist
• autonomous discovery
• first-principles calculations
• excitonic states
• quantum materials