GxP-Agent：基于过程DAG拓扑的可靠临床试验编程LLM代理系统
原标题：GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agents
AI 摘要
GxP-Agent 是一个多智能体系统，将临床试验编程的监管流程编码为有向无环图（DAG），分解为15个领域特定节点，由具备pharmaverse技能上下文的工人代理执行，并包含验证门和条件重试。在CDISC-Bench基准测试中，GxP-Agent使用Claude Sonnet 4.6实现了100%的结构匹配，而所有单代理和扁平多代理方法均为0%，表明编码领域过程知识为图拓扑是实现可靠、符合GxP的临床试验编程的关键。
正文节选
GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agents Abstract 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 proce