# Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning

arXiv: https://arxiv.org/abs/2503.16463 · HTML: https://mlsanity.com/paper/2503.16463/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [Towards Conversational Diagnostic AI](https://mlsanity.com/paper/2401.05654/) (2024)
- [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023)
- [UltraMedical: Building Specialized Generalists in Biomedicine](https://mlsanity.com/paper/2406.03949/) (2024)
- [A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets](https://mlsanity.com/paper/2204.08997/) (2022)
- [Language Model Alignment with Elastic Reset](https://mlsanity.com/paper/2312.07551/) (2023)
- [Towards Automatic Evaluation for LLMs' Clinical Capabilities: Metric, Data, and Algorithm](https://mlsanity.com/paper/2403.16446/) (2024)

## Built on by (most cited first, 3 of 3)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.19630/) (2025)
- [Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes](https://mlsanity.com/paper/2601.21551/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have shown promising results in medical diagnosis, with some studies indicating superior performance compared to human physicians in specific scenarios. However, the diagnostic capabilities of LLMs are often overestimated, as their performance significantly deteriorates in interactive diagnostic settings that require active information gathering. This study investigates the underlying mechanisms behind the performance degradation phenomenon and proposes a solution. We identified that the primary deficiency of LLMs lies in the initial diagnosis phase, particularly in information-gathering efficiency and initial diagnosis formation, rather than in the subsequent differential diagnosis phase. To address this limitation, we developed a plug-and-play method enhanced (PPME) LLM agent, leveraging over 3.5 million electronic medical records from Chinese and American healthcare facilities. Our approach integrates specialized models for initial disease diagnosis and inquiry into the history of the present illness, trained through supervised and reinforcement learning techniques. The experimental results indicate that the PPME LLM achieved over 30% improvement compared to baselines. The final diagnostic accuracy of the PPME LLM in interactive diagnostic scenarios approached levels comparable to those achieved using complete clinical data. These findings suggest a promising potential for developing autonomous diagnostic systems, although further validation studies are needed.