发表机构
Harrisburg University of Science and Technology（哈里斯堡科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于流程DAG拓扑的多智能体系统GxP-Agent，在临床试验编程任务上显著优于现有方法，实现了高结构匹配率，验证了编码领域流程知识为图拓扑的有效性。
AI 中文摘要
临床试验编程是指将研究方案转换为符合CDISC标准、可用于分析的数据集，是监管申报的瓶颈环节，但基于大语言模型（LLM）的代码生成在该任务上表现极差：对5种前沿模型各进行11次单样本尝试，均未生成有效的受试者层面分析数据集。我们提出GxP-Agent，这一多智能体系统将监管流程的顺序编码为有向无环图（DAG），将整体数据集生成分解为15个领域特定节点，由具备pharmaverse技能上下文、验证门控和条件重试机制的工作智能体执行。在基于FDA试点申报CDISCPilot01构建的新执行基准CDISC-Bench（含254名受试者、49个真实ADSL变量）上，配备Claude Sonnet 4.6的GxP-Agent在3次独立运行中均达到100%结构匹配（49个变量全部正确，254条记录全部正确），而最佳检索增强基准的结构匹配率为59.2%，所有单智能体及扁平多智能体方法的结构匹配率均为0%。该DAG拓扑结构还能让性能较弱的模型发挥作用：在相同DAG下，GPT-4.1的平均结构匹配率达59.2%，而在其他所有架构下其得分均为0%。该方法还可推广至ADAE（不良事件数据集，含9节点分支DAG、55个变量、1191条记录），首次尝试即达到100%结构匹配。这些结果表明，将领域流程知识编码为图拓扑结构而非仅依赖LLM推理，是实现符合GxP标准的可靠临床试验编程的关键推动因素。
英文摘要
Clinical trial programming -- transforming study protocols into analysis-ready datasets under CDISC standards -- is a bottleneck in regulatory submissions, yet LLM-based code generation fails catastrophically on this task: across 11 single-shot attempts with five frontier models, none produces a valid subject-level analysis dataset. We introduce GxP-Agent, a multi-agent system that encodes regulatory process ordering as a directed acyclic graph (DAG), decomposing monolithic dataset generation into 15 domain-specific nodes executed by worker agents with pharmaverse skill context, validation gates, and conditional retry. On CDISC-Bench, a new execution-based benchmark built from the FDA pilot submission CDISCPilot01 (254 subjects, 49 ground-truth ADSL variables), GxP-Agent with Claude Sonnet 4.6 achieves 100% structural match (49/49 variables, 254 correct records) across three independent runs, compared to 59.2% for the best retrieval-augmented baseline and 0% for all single-agent and flat multi-agent approaches. The DAG topology also enables weaker models: GPT-4.1 achieves 59.2% mean structural match under the same DAG, where it scores 0% under every other architecture. The approach generalizes to ADAE (adverse events; 9-node branching DAG, 55 variables, 1,191 records), achieving 100% structural match on the first attempt. These results demonstrate that encoding domain process knowledge as graph topology -- rather than relying on LLM reasoning alone -- is a key enabler for reliable, GxP-compliant clinical trial programming.
CommentsPreprint. 9 pages main text, 3 figures, plus references and appendix
