# Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model

arXiv: https://arxiv.org/abs/2605.14723 · HTML: https://mlsanity.com/paper/2605.14723/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and surgical world models, one of 11 directions in World models.
- Builds on 14 of its 51 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- World models / [Medical and surgical world models](https://mlsanity.com/wm/medical-and-surgical-world-models/)

## Builds on (most cited first, 14 of 14)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [Deep Reinforcement Learning for Sepsis Treatment](https://mlsanity.com/paper/1711.09602/) (2017)
- [Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs](https://mlsanity.com/paper/2412.16178/) (2024)
- [Model-Based Reinforcement Learning for Sepsis Treatment](https://mlsanity.com/paper/1811.09602/) (2018)
- [medDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support](https://mlsanity.com/paper/2505.19785/) (2025)
- [Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination](https://mlsanity.com/paper/2405.18556/) (2024)
- [Model-Free Reinforcement Learning for Automated Fluid Administration in Critical Care](https://mlsanity.com/paper/2401.06299/) (2024)

## Built on by (most cited first, 2 of 2)

- [Learning response-aware patient dynamics for respiratory support](https://mlsanity.com/paper/2609.32782/) (2026)
- [PatientWM: Towards Generalizable Clinical World Models via Unified Patient States](https://mlsanity.com/paper/2610.17059/) (2026)

## Abstract (arXiv)

Sepsis management in the ICU requires sequential treatment decisions under rapidly evolving patient physiology. Although large language models (LLMs) encode broad clinical knowledge and can reason over guidelines, they are not inherently grounded in action-conditioned patient dynamics. We introduce SepsisAgent, a world model-augmented LLM agent for sepsis treatment recommendation. SepsisAgent uses a learned Clinical World Model to simulate patient responses under candidate fluid--vasopressor interventions, and follows a propose--simulate--refine workflow before committing to a prescription. We first show that world-model access alone yields inconsistent LLM decision performance, motivating agent-specific training. We then train SepsisAgent through a three-stage curriculum: patient-dynamics supervised fine-tuning, propose--simulate--refine behavior cloning, and world-model-based agentic reinforcement learning. On MIMIC-IV sepsis trajectories, SepsisAgent outperforms all traditional RL and LLM-based baselines in off-policy value while achieving the best safety profile under guideline adherence and unsafe-action metrics. Further analysis shows that repeated interaction with the Clinical World Model enables the agent to learn regularities in patient evolution, which remain useful even when simulator access is removed.