[Application and progress of artificial intelligence agents in drug development].

Drug discovery is confronted with formidable challenges including high costs, significant risks, and prolonged timelines, necessitating disruptive technologies capable of systematically improving efficiency, enabling accurate predictions, and mitigating failure risks. Artificial intelligence (AI) agent-an emerging intelligent paradigm powered by large language models-hold immense potential to transform the entire drug development pipeline. Their core capability lies in performing autonomous reasoning, planning, and tool utilization oriented toward complex scientific objectives, thereby integrating and orchestrating multiple research stages and transitioning AI from a mere "tool" to an "active collaborator". On one hand, through knowledge integration and hypothesis generation, AI agents can identify underexplored targets and novel mechanisms. On the other hand, they can automate complex tasks such as molecular design, optimization, and synthesis planning, and close the loop from virtual design to physical experimentation by interfacing with automated experimental platforms. Moreover, AI agents are evolving toward higher-level paradigms, including the development of integrated drug design platforms and general-purpose biomedical agents. This review systematically outlines the core architecture of AI agents, highlights their applications across key stages of drug development, and discusses current limitations along with future directions, with the aim of providing a reference for researchers in related fields.