用图结构管理临床试验编程流程，让大模型稳定生成合规数据集。
GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agents
- 将临床试验流程建模为有向无环图，分步由专业代理执行任务
- 在254例受试者数据上实现100%结构匹配，远超其他方法
- 适合医药研发、监管合规领域，尤其提升弱模型可靠性
临床试验编程——将研究方案转化为符合CDISC标准的分析就绪数据集——是监管提交中的瓶颈。现有基于大模型的代码生成在该任务上表现失败：在五种前沿模型的11次单次尝试中，均未生成有效的受试者级分析数据集。本文提出GxP-Agent，一个将法规流程顺序编码为有向无环图（DAG）的多智能体系统，将整体数据生成分解为15个领域特定节点，由具备药学知识上下文的工作者代理执行，包含验证关卡和条件重试机制。在新构建的执行基准CDISC-Bench上（基于FDA试点提交CDISCPilot01，含254名受试者、49个真实数据集变量），GxP-Agent结合Claude Sonnet 4.6，在三次独立运行中实现100%结构匹配（49/49变量，254条正确记录），优于最佳检索增强基线的59.2%，而所有单智能体与扁平多智能体方法均为0%。该图结构还使较弱模型受益：GPT-4.1在相同DAG下达59.2%平均结构匹配，此前在所有架构下均为0%。该方法推广至不良事件（ADAE）任务（9节点分支图，55变量，1,191条记录），首次尝试即实现100%结构匹配。结果表明，将领域流程知识编码为图拓扑，而非依赖大模型自身推理，是实现可靠、GxP合规临床试验编程的关键。
原文摘要 · Abstract (English)
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.
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。