Lipid nanoparticles (LNPs) are among the most clinically mature platforms for nucleic acid delivery, yet designing lipids that are both effective and biologically safe remains a major bottleneck. In practical screening, toxicity is a decision-level constraint: if a lipid is toxic, its efficiency prediction is clinically irrelevant. We propose LipoAgent, a safety-aware multi-agent LLM framework for lipid discovery. LipoAgent combines domain-specific finetuning with a conditional prediction objective that enforces toxicity as a prerequisite for efficiency prediction, and further improves reliability via multi-agent verification with lightweight human oversight when disagreement persists. Across multiple foundation models, LipoAgent achieves an average 32% relative improvement in mRNA transfection efficiency prediction compared with other reported models for lipid design. Wet-lab validation confirms that virtual screening rankings reliably translate to biological transfection outcomes. The code is publicly available at https://github.com/SAI-Lab-NYU/LipoAgent.git.
@article{arxiv.2605.25250,
title = {LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design},
author = {Leshu Li and An Lu and Haiyu Wang and Zhibin Feng and Conghui Duan and Qing Bao and Zongmin Zhao and Sai Qian Zhang},
journal= {arXiv preprint arXiv:2605.25250},
year = {2026}
}