医疗AI开发者注意了：MDIA用架构设计而非提示工程就超越了专业临床模型，做临床决策系统的团队值得研究其7节点路由和药物安全门控设计。
研究者提出MDIA，一个由7个专科路由节点组成的多智能体临床推理图，在HealthBench Professional基准（525个病例）上，使用未微调的GPT-5.4-2026-03-05模型达到0.6272分，比OpenAI的ChatGPT for Clinicians高出3.72个百分点。性能提升主要来自系统架构设计，包括专科路由、多轮上下文保持、药物状态安全门控、站点过滤搜索、长度感知合成和引擎级可靠性。实验还发现，使用不同模型作为评分者时结果差异显著，例如Gemini 2.5 Pro评分时MDIA得分0.6585，表明评估需要多个独立评分模型。该研究证明，智能体临床基准性能既取决于基础模型，也取决于编排架构。
MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional
Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can come from architectural and engine-level design. We present MDIA, a Multi-agent Diagnostic Intelligence Agent implemented as a 7-node specialty-routed clinical reasoning graph, on the full HealthBench Professional benchmark (n = 525), on a non-fine-tuned LLM. MDIA achieves 0.6272 under OpenAI's GPT-5.4-2026-03-05, which is +3.72 pp above the performance of OpenAI's ChatGPT for Clinicians. The experimental work shows that performance lift is attributable to system architecture: specialty routing, multi-turn context preservation, drug-state safety gating, site-filtered search, length-aware synthesis, and engine-level reliability. These findings support the view that agentic clinical benchmark performance is shaped both by the underlying foundation model and the orchestration architecture. Nevertheless, we also noticed notable differences when using other models as a grader; in particular, when using Gemini 2.5 Pro, MDIA scored 0.6585, which suggests that the choice of grader is a source of variability. Robust evaluation of LLMs would therefore require assessment across several independent grader models.