{"ID":2882409,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10760","arxiv_id":"2508.10760","title":"FROGENT: An End-to-End Full-process Drug Design Multi-Agent System","abstract":"Drug discovery is a complex, multi-step pipeline that remains heavily dependent on manual, experience-driven operations; meanwhile, existing customized artificial intelligence tools are fragmented across web applications, desktop software, and code libraries, resulting in incompatible interfaces and inefficient, burdensome workflows. To overcome these challenges, we propose FROGENT, a full-process drug design multi-agent system that leverages the planning, reasoning, and tool-use capabilities of large language models (LLMs) to unify drug discovery within a closed-loop and autonomous framework. FROGENT is a collaborative multi-agent system comprising a central Orchestrate Agent for strategic workflow coordination and three distributed agents, Retrieve, Forge, and Gauge, that employ dynamic biochemical databases, extensible tool libraries, and task-specific computational models via the Model Context Protocol. This architecture enables end-to-end execution of complex drug discovery pipelines, covering target identification, small-molecule generation, peptide optimization, and retrosynthetic planning. Across eight benchmarks spanning core drug discovery tasks, FROGENT consistently outperforms six increasingly advanced ReAct-style agents. Case studies further demonstrate its practicality and generalization across real-world small-molecule and peptide design scenarios. Overall, FROGENT not only achieves substantial gains in efficiency and accuracy, but also demonstrates the potential of LLM-based agentic systems to autonomously orchestrate drug development pipelines, reducing, or even replacing, reliance on manual, experience-driven human intervention.","short_abstract":"Drug discovery is a complex, multi-step pipeline that remains heavily dependent on manual, experience-driven operations; meanwhile, existing customized artificial intelligence tools are fragmented across web applications, desktop software, and code libraries, resulting in incompatible interfaces and inefficient, burden...","url_abs":"https://arxiv.org/abs/2508.10760","url_pdf":"https://arxiv.org/pdf/2508.10760v2","authors":"[\"Qihua Pan\",\"Dong Xu\",\"Qianwei Yang\",\"Jenna Xinyi Yao\",\"Sisi Yuan\",\"Zexuan Zhu\",\"Jianqiang Li\",\"Junkai Ji\"]","published":"2025-08-14T15:45:53Z","proceeding":"q-bio.BM","tasks":"[\"q-bio.BM\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}