LLM-Guided Open Hypothesis Learning from Autonomous Scanning Probe Microscopy Experiments

2026-05-07

AI Summary

Current autonomous microscopy experiments are often constrained by predefined assumptions, limiting their ability to uncover novel physical laws from data. This work proposes an open-hypothesis learning framework that integrates symbolic regression with large language model (LLM)-driven assessments of physical plausibility to automatically generate and filter interpretable analytical expressions from sparse scanning probe microscopy data. Notably, it introduces the first application of LLMs to evaluate the physical validity of symbolic regression–derived equations. By combining adaptive scanning with piezoresponse force microscopy (PFM), the method successfully evolves a voltage–time growth law consistent with ferroelectric domain wall dynamics using only five initial measurement points, demonstrating its effectiveness in transcending preset assumptions and autonomously discovering physically meaningful, interpretable laws.

Abstract

Autonomous experimentation has transformed microscopy and materials discovery by enabling closed-loop optimization including imaging and spectroscopy tuning, strucutre property relationship discovery, and exploration of combinatorial libraries. However, most current workflows remain limited to selecting measurements within fixed objective or hypothesis spaces, rather than generating new physical models from experimental data. Here, we introduce an open hypothesis-learning framework that combines symbolic regression with large-language-model-based physical evaluation and implement it for autonomous scanning probe microscopy. Symbolic regression generates candidate analytical relationships directly from sparse measurements, while the language-model evaluator ranks these candidates according to physical plausibility, scaling behavior, and consistency with known mechanisms. We demonstrate the approach on autonomous piezoresponse force microscopy measurements of ferroelectric domain switching in a PZT thin film. Starting from five seed measurements, the workflow evolves from physically incomplete candidate expressions toward interpretable voltage-time growth laws consistent with kinetic domain-wall motion. This work extends autonomous microscopy from closed-loop optimization toward open hypothesis discovery, where candidate physical laws emerge from the experiment itself rather than being specified in advance. More broadly, the framework establishes a route for integrating symbolic regression, physical reasoning, and adaptive experimentation into hierarchical autonomous scientific workflows.

Problem

• autonomous experimentation
• hypothesis discovery
• physical model generation
• scanning probe microscopy
• open hypothesis learning

Innovation

• open hypothesis learning
• symbolic regression
• large language model
• autonomous microscopy
• physical law discovery