CohortFlow: steerable clinical-cohort curation agent with localized semantic correction

KEY POINTS

1. Researchers introduce CohortFlow, an agent that represents natural-language corrections as localized updates to a structured cohort specification and maintains a persistent execution graph with recorded semantic dependencies so only affected computations are invalidated.
2. On 100 scenarios (126 correction turns) derived from clinical-trial eligibility criteria, localized steering matched full-regeneration requirement micro-F1 (77.0% vs 76.4%, p=0.493) while reducing mean correction latency by 64.8% after completion, 44.3% during execution, and cutting model calls by 38.1%; a MIMIC proof-of-concept ran all 13 cohort states and showed selective recomputation of changed or dependent nodes.
3. Localized semantic steering can substantially cut correction latency and model calls while maintaining requirement-level accuracy, making interactive cohort curation with evolving eligibility criteria more efficient.