📝 SummarXiv

Abstract

Molecular design plays a critical role in advancing fields such as drug discovery, materials science, and chemical engineering. This work introduces the Multi-Objective Large Language Model for Molecular Design (MOLLM), a novel framework that combines domain-specific knowledge with the adaptability of large language models to optimize molecular properties across multiple objectives. Leveraging in-context learning and multi-objective optimization, MOLLM achieves superior performance and innovation, consistently surpassing state-of-the-art (SOTA) methods. We significantly improve the efficiency of our framework, making it 14 times faster and substantially more cost-effective without compromising performance compared to the latest similar work. Our results demonstrate that MOLLM consistently outperforms SOTA models across experiments and excels on the PMO benchmark. In addition, we provide extensive ablation studies and analysis to evaluate the effectiveness of each component and the quality of the output molecules.