# From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM

arXiv: https://arxiv.org/abs/2603.23520 · HTML: https://mlsanity.com/paper/2603.23520/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Knowledge Graph Prompting for Multi-Document Question Answering](https://mlsanity.com/paper/2308.11730/) (2023)
- [Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)](https://mlsanity.com/paper/2510.22954/) (2025)
- [GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information](https://mlsanity.com/paper/2304.09667/) (2023)
- [HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs](https://mlsanity.com/paper/2311.09774/) (2023)
- [Leveraging Large Language Models for NLG Evaluation: Advances and Challenges](https://mlsanity.com/paper/2401.07103/) (2024)
- [On Context Utilization in Summarization with Large Language Models](https://mlsanity.com/paper/2310.10570/) (2023)
- [LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2401.00757/) (2024)
- [Capabilities of GPT-5 across critical domains: Is it the next breakthrough?](https://mlsanity.com/paper/2508.19259/) (2025)
- [Automatic construction of Chinese herbal prescription from tongue image via CNNs and auxiliary latent therapy topics](https://mlsanity.com/paper/1802.02203/) (2018)
- [Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2504.07754/) (2025)
- [Tianyi: A Traditional Chinese Medicine all-rounder language model and its Real-World Clinical Practice](https://mlsanity.com/paper/2505.13156/) (2025)
- [Demo: Statistically Significant Results On Biases and Errors of LLMs Do Not Guarantee Generalizable Results](https://mlsanity.com/paper/2511.02246/) (2025)

## Abstract (arXiv)

Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models.