arXiv cs.AI· Neil Chen, Adrian Serapio, Hanxue Gu, Evan Lee, Kang Wang, Yang Yang·· 11 小时前AI 评分31
CohortFlow：支持局部语义修正的可操控临床队列构建智能体
CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction
AI 导读
CohortFlow 是一个可操控的临床队列构建智能体，将自然语言修正表示为对结构化队列规范的局部更新，并与持久化执行图协调，只重算受影响的计算。
正文 · 原文
Abstract:Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion and 44.3% during execution, with 38.1% fewer model calls. In a separate proof-of-concept evaluation over MIMIC, all 13 cohort states execute successfully, while correction trajectories demonstrate selective preservation of unaffected computations and recomputation of changed or dependent nodes. Together, these results show that localized semantic steering can substantially reduce correction latency and model calls while maintaining strong requirement-level accuracy.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36100 [cs.AI] |
| (or arXiv:2610.36100v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36100 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Neil Chen [view email]
[v1]
Mon, 26 Oct 2026 18:16:29 UTC (788 KB)
来源：arXiv cs.AI · arxiv.org