On July 7, 2026, Weill Cornell Medicine researchers published EmulatRx in Nature Communications, describing a five-agent LLM framework for clinical-trial design using real-world patient data. The system splits work across Supervisor, Trialist, Informatician, Clinician and Statistician agents, grounding trial-protocol generation, cohort construction and causal analysis in EHR datasets such as MIMIC-IV and INSIGHT. The paper says EmulatRx uses structured agent handoffs, LangGraph-based control flow, centralized serializable state, an LLM response cache and fixed random seeds for downstream statistical tools. It evaluated acute-disease trial-design tasks using MIMIC-IV data and chronic-disease tasks using the INSIGHT Network across five New York City health systems. The authors benchmarked several model bases, including GPT-4o, Phi-4, DeepSeek-R1 and Gemma 3, across parsing, SQL generation, causal analysis and clinician-response tasks. Weill Cornell says broader validation across other health systems and patient-data types is still required before clinical or commercial deployment.