ICML 2026 Workshop on Structured Data for Health · 2026 · Accepted
Distilling Expert-level Planning for Real-world Diabetes Prescribing
Expert planning distillation and dynamic search for reimbursement-aware diabetes prescribing.
Paper
Abstract
Real-world prescribing is constrained not only by clinical appropriateness but also by reimbursement policy, prior treatment history, and patient preference, which remain under-modeled in exam-style medical QA training and evaluation. We present a practical framework for expert-usable clinical agents for diabetes prescribing that combines expert planning distillation—distilling an expert prescribing workflow from patient assessment and safety checks to candidate regimen selection and reimbursement verification—with dynamic search over guidelines, reimbursement criteria, drug information, and up-to-date references. To evaluate real-world prescribability, we construct an EMR-derived diabetes prescribing benchmark from 170 de-identified real-world patient cases and evaluate on 340 test instances with a clinician-aligned, reimbursement-aware rubric. On this benchmark, our expert planning distillation and dynamic search improve reimbursement-aware prescribing quality over general and biomedical baselines and approach the performance of frontier proprietary models.
Resources
Read and cite this paper
@inproceedings{diabetesplanning2026,
title = {Distilling Expert-level Planning for Real-world Diabetes Prescribing},
author = {Park, Yein and Park, Sihyeon and Roh, Taeyun and Sung, Mujeen and Yun, Jaehoon and Lee, Sooyeon and Lee, Sanghoon and Kang, Jaewoo},
year = {2026},
booktitle = {ICML 2026 Workshop on Structured Data for Health},
url = {https://openreview.net/forum?id=WZvLoCILdg}
}