AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery

TL;DR

AIonopedia is a novel LLM-based agent that orchestrates multimodal learning to improve ionic liquid discovery by enabling accurate property prediction, molecular screening, and real-world validation, thus accelerating the discovery process.

Contribution

This work introduces the first LLM agent for ionic liquid discovery, integrating multimodal models and hierarchical search for enhanced property prediction and molecular design.

Findings

Superior performance on a new IL dataset

Effective IL modification demonstrated

Successful real-world wet-lab validation

Abstract

The discovery of novel Ionic Liquids (ILs) is hindered by critical challenges in property prediction, including limited data, poor model accuracy, and fragmented workflows. Leveraging the power of Large Language Models (LLMs), we introduce AIonopedia, to the best of our knowledge, the first LLM agent for IL discovery. Powered by an LLM-augmented multimodal domain foundation model for ILs, AIonopedia enables accurate property predictions and incorporates a hierarchical search architecture for molecular screening and design. Trained and evaluated on a newly curated and comprehensive IL dataset, our model delivers superior performance. Complementing these results, evaluations on literature-reported systems indicate that the agent can perform effective IL modification. Moving beyond offline tests, the practical efficacy was further confirmed through real-world wet-lab validation, in which the agent demonstrated exceptional generalization capabilities on challenging out-of-distribution tasks, underscoring its ability to accelerate real-world IL discovery.