AI Agents in Drug Discovery

2025-10-30

AI Summary

This study addresses the prolonged timelines, poor reproducibility, and high human dependency inherent in conventional drug discovery. We propose the first end-to-end AI agent system designed for real-world pharmaceutical R&D. Methodologically, we develop a multi-agent architecture integrating large language models with perception, computation, action, and memory modules—incorporating ReAct, Reflection, Supervisor, and Swarm mechanisms—and tightly couple it with robotic experimental platforms to enable literature synthesis, toxicity prediction, molecular synthesis, and closed-loop hypothesis optimization. Our key contribution is the first demonstration of a fully autonomous “reasoning–experimentation–learning”闭环 in actual drug development, alongside a traceable, quantifiable scientific agent paradigm. Empirical evaluation shows that critical workflow cycles are reduced from months to hours, markedly improving efficiency, reproducibility, scalability, and scientific rigor.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Artificial intelligence (AI) agents are emerging as transformative tools in drug discovery, with the ability to autonomously reason, act, and learn through complicated research workflows. Building on large language models (LLMs) coupled with perception, computation, action, and memory tools, these agentic AI systems could integrate diverse biomedical data, execute tasks, carry out experiments via robotic platforms, and iteratively refine hypotheses in closed loops. We provide a conceptual and technical overview of agentic AI architectures, ranging from ReAct and Reflection to Supervisor and Swarm systems, and illustrate their applications across key stages of drug discovery, including literature synthesis, toxicity prediction, automated protocol generation, small-molecule synthesis, drug repurposing, and end-to-end decision-making. To our knowledge, this represents the first comprehensive work to present real-world implementations and quantifiable impacts of agentic AI systems deployed in operational drug discovery settings. Early implementations demonstrate substantial gains in speed, reproducibility, and scalability, compressing workflows that once took months into hours while maintaining scientific traceability. We discuss the current challenges related to data heterogeneity, system reliability, privacy, and benchmarking, and outline future directions towards technology in support of science and translation.

Problem

• AI agents autonomously reason and act in drug discovery workflows
• Integrate biomedical data and execute experiments via robotic platforms
• Address challenges in data heterogeneity and system reliability

Innovation

• LLM-based agents autonomously execute drug discovery workflows
• Integrate biomedical data and robotic experiments via closed loops
• Implement architectures like ReAct and Swarm for end-to-end decisions