The US Department of Health and Human Services (HHS), through the Advanced Research Projects Agency for Health (ARPA-H), on September 30, 2026 launched the Simulation-augmented, Real-time Platform Adaptive Seamless Trials (SURPASS) program alongside three complementary projects aimed at restructuring how clinical trials are designed and conducted in the United States. The HHS notes that drug and biologic development often takes more than a decade, costs up to USD 2 billion on average, and fails more than 90% of the time.
SURPASS will pursue three technical areas. The first is a phaseless design engine that integrates digital twins and other predictive models into trial design, simulating clinical and operational outcomes before launch. The second is a continuous inference engine enabling always-valid, real-time or on-demand analysis and rapid trial adaptations, with the stated aim of reducing reliance on large conventional control groups while maintaining rigorous evidence generation. The third is an agentic operations layer to automate trial start-up, treatment-arm onboarding, data collection, and dataset construction.
ARPA-H said SURPASS ultimately aims to shorten clinical development from more than a decade to less than four years by combining predictive models, shared trial infrastructure, common control groups, and real-time analysis.
Three separate projects will address supporting trial infrastructure. STACK will use artificial intelligence to accelerate site activation and help research-naïve sites become capable of running clinical studies. COMMONS will develop a privacy-by-design architecture for consent at national scale and access to regulatory-grade data, while CINCH will enable patients to contribute real-world data and receive care-navigation support, including faster connections to potentially suitable clinical trials.
Beyond individual trials, ARPA-H stated that the program is intended to produce publicly available regulatory documents, validated standards, and real-world demonstrations of modernized trial methods that sponsors, sites, regulators, and technology developers could adopt across disease areas.