# CohortFlow: steerable agent for clinical cohort curation

Digest AI · Agents & Tools · published 2026-10-28T04:00:00Z

Canonical: https://digestai.news/story/cohortflow-steerable-agent-for-clinical-cohort-curation

## Summary

The system is capable of making localized updates to a structured cohort specification and reconciling these changes with a persistent execution graph. This allows it to reduce correction latency by up to 64.8% compared to full regeneration using the same model, as demonstrated on 100 scenarios derived from clinical trial eligibility criteria. CohortFlow also shows promise in reducing the number of model calls required for corrections and maintaining high accuracy.

## Key points

- CohortFlow reduces correction latency by up to 64.8%
- Localized steering achieves a micro-F1 score of 77.0%
- It maintains strong requirement-level accuracy in MIMIC evaluations

## Why it matters

This tool could significantly improve the efficiency and effectiveness of medical research, particularly in clinical trials.

## Sources

1. [CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction](https://arxiv.org/abs/2610.36100) (arXiv cs.AI, 2026-10-28, primary source)

## Cite

Digest AI, "CohortFlow: steerable agent for clinical cohort curation", 28 October 2026, https://digestai.news/story/cohortflow-steerable-agent-for-clinical-cohort-curation

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/cohortflow-steerable-agent-for-clinical-cohort-curation.json