Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model

• URL: http://arxiv.org/abs/2605.14723v1
• Date: Thu, 14 May 2026 11:50:00 GMT
• Title: Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model
• Abstract summary: We introduce SepsisAgent, a world model-augmented LLM agent for sepsis treatment recommendation.<n>SepsisAgent uses a learned Clinical World Model to simulate patient responses under candidate fluid--vasopressor interventions.
• Score: 57.78184285979881
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases [71.12461204050985]
  MedSP1000 is an SP-derived interactive benchmark for clinical-agent evaluation.<n>It converts peer-reviewed SP teaching cases into executable scenarios with defined SP case scripts, clinical environment contexts, and human-validated structured rubrics.<n>Applying MedSP1000 to a range of general-purpose and medically specialized LLMs, we find that performance on static benchmarks does not reliably translate to such educational scenarios.
  arXiv  Detail & Related papers  (2026-06-03T17:17:16Z)
• Learning POMDP World Models from Observations with Language-Model Priors [52.11151769796862]
  Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for internal world models.<n>We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge.<n>We show that emphPinductor matches the performance and sample efficiency of LLM-based POMDP learning methods.
  arXiv  Detail & Related papers  (2026-05-13T16:18:15Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• EHRWorld: A Patient-Centric Medical World Model for Long-Horizon Clinical Trajectories [16.355665390403654]
  Recent large language models (LLMs) have achieved strong performance on static medical reasoning tasks.<n>We show that LLMs only incorporating medical knowledge struggle to maintain consistent patient states under sequential interventions.<n>We introduce EHRWorld, a patient-centric medical world model trained under a causal sequential paradigm.
  arXiv  Detail & Related papers  (2026-02-03T14:12:24Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• How many patients could we save with LLM priors? [1.8421433205488897]
  We present a novel framework for hierarchical Bayesian modeling of adverse events in multi-center clinical trials.<n>Our methodology directly obtains priors from the model using a pre-trained large language model (LLMs)<n>This methodology paves the way for more efficient and expert-informed clinical trial design.
  arXiv  Detail & Related papers  (2025-09-04T14:23:35Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• Are Large Language Models Dynamic Treatment Planners? An In Silico Study from a Prior Knowledge Injection Angle [3.0391297540732545]
  We evaluate large language models (LLMs) as dynamic insulin dosing agents in an in silico Type 1 diabetes simulator.<n>Our results indicate that carefully designed zero-shot prompts enable smaller LLMs to achieve comparable or superior clinical performance.<n>LLMs exhibit notable limitations, such as overly aggressive insulin dosing when prompted with chain-of-thought.
  arXiv  Detail & Related papers  (2025-08-06T13:46:02Z)
• DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue [18.814676128928234]
  Large language models (LLMs) have demonstrated excellent capabilities in the field of biomedical question answering, but their application in real-world clinical consultations still faces core challenges.<n>We propose Ours, a reinforcement learning (RL)-based multi-agent collaborative framework that models medical consultations as a dynamic decision-making process under uncertainty.<n>Our approach shows immense practical value by reducing misdiagnosis risks in time-pressured settings, freeing clinicians for complex cases, and pioneering a strategy to optimize medical resource allocation and alleviate workforce shortages.
  arXiv  Detail & Related papers  (2025-05-26T07:48:14Z)
• Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions [26.167030665482184]
  We introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents.<n>Unlike prior approaches, our framework requires doctor agents to actively engage with patients through multi-turn conversations.<n>We incorporate self improvement mechanisms that allow models to iteratively refine their diagnostic strategies.
  arXiv  Detail & Related papers  (2025-03-28T17:59:53Z)
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence [68.05876437208505]
  We present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow.<n>We also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses.
  arXiv  Detail & Related papers  (2024-12-02T15:25:02Z)
• Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator [21.60103376506254]
  Large Language Models (LLMs) have demonstrated remarkable proficiency in human interactions. This paper introduces the Automated Interactive Evaluation (AIE) framework and the State-Aware Patient Simulator (SAPS) AIE and SAPS provide a dynamic, realistic platform for assessing LLMs through multi-turn doctor-patient simulations.
  arXiv  Detail & Related papers  (2024-03-13T13:04:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.