用多智能体协作让大模型自动写药研代码，提升研发效率
DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
- 设计规划与指导双智能体，协同完成药物发现编程任务
- 在药物-靶点互作任务中，ROC-AUC比ReAct提升4.92%
- 适合医药AI研究者快速实现复杂算法，降低技术门槛
大型语言模型（LLM）的进展为加速药物发现带来了新可能，但核心问题仍在于如何将理论构想转化为药研领域高度专业化的可靠程序实现。为此，我们提出DrugAgent，一个用于自动化药物发现机器学习编程的多智能体框架。该框架包含一个负责制定高层策略的LLM规划器，以及一个在实现过程中识别并整合领域知识的LLM指导者。我们在三个典型的药物发现任务上进行了案例研究。结果表明，DrugAgent持续优于主流基线方法，尤其在药物-靶点相互作用（DTI）任务中，相比ReAct实现4.92%的相对ROC-AUC提升。项目已公开，地址：https://anonymous.4open.science/r/drugagent-5C42/
原文摘要 · Abstract (English)
Recent progress in Large Language Models (LLMs) has drawn attention to their potential for accelerating drug discovery. However, a central problem remains: translating theoretical ideas into robust implementations in the highly specialized context of pharmaceutical research. This limitation prevents practitioners from making full use of the latest AI developments in drug discovery. To address this challenge, we introduce DrugAgent, a multi-agent framework that automates machine learning (ML) programming for drug discovery tasks. DrugAgent employs an LLM Planner that formulates high-level ideas and an LLM Instructor that identifies and integrates domain knowledge when implementing those ideas. We present case studies on three representative drug discovery tasks. Our results show that DrugAgent consistently outperforms leading baselines, including a relative improvement of 4.92% in ROC-AUC compared to ReAct for drug-target interaction (DTI). DrugAgent is publicly available at https://anonymous.4open.science/r/drugagent-5C42/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。