LUMIR: an LLM-Driven Unified Agent Framework for Multi-task Infrared Spectroscopy Reasoning

TL;DR

LUMIR leverages large language models and structured literature knowledge to enable accurate, low-data infrared spectral analysis across diverse applications, surpassing traditional methods in resource-limited settings.

Contribution

This paper introduces LUMIR, a novel LLM-driven framework that unifies spectral preprocessing, feature extraction, and prediction, demonstrating effective multi-task infrared spectroscopy reasoning with minimal data.

Findings

LUMIR achieves comparable or better performance than traditional models.

Effective in resource-limited and diverse datasets.

Automates spectral interpretation using literature-guided few-shot learning.

Abstract

Infrared spectroscopy enables rapid, non destructive analysis of chemical and material properties, yet high dimensional signals and overlapping bands hinder conventional chemometric methods. Large language models (LLMs), with strong generalization and reasoning capabilities, offer new opportunities for automated spectral interpretation, but their potential in this domain remains largely untapped. This study introduces LUMIR (LLM-driven Unified agent framework for Multi-task Infrared spectroscopy Reasoning), an agent based framework designed to achieve accurate infrared spectral analysis under low data conditions. LUMIR integrates a structured literature knowledge base, automated preprocessing, feature extraction, and predictive modeling into a unified pipeline. By mining peer reviewed spectroscopy studies, it identifies validated preprocessing and feature derivation strategies, transforms spectra into low dimensional representations, and applies few-shot prompts for classification, regression, and anomaly detection. The framework was validated on diverse datasets, including the publicly available Milk near-infrared dataset, Chinese medicinal herbs, Citri Reticulatae Pericarpium(CRP) with different storage durations, an industrial wastewater COD dataset, and two additional public benchmarks, Tecator and Corn. Across these tasks, LUMIR achieved performance comparable to or surpassing established machine learning and deep learning models, particularly in resource limited settings. This work demonstrates that combining structured literature guidance with few-shot learning enables robust, scalable, and automated spectral interpretation. LUMIR establishes a new paradigm for applying LLMs to infrared spectroscopy, offering high accuracy with minimal labeled data and broad applicability across scientific and industrial domains.