臨床世界モデルとの対話によるLLM内の患者動態のエージェント化
Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model
敗血症治療の逐次意思決定を改善するため、臨床世界モデルで患者反応をシミュレートし、提案・シミュレート・修正の流れで処方を決定するLLMエージェントSepsisAgentを導入。3段階カリキュラムで訓練し、MIMIC-IVデータで既存手法を上回る性能と安全性を達成した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Minghao Wu, Yuting Yan, Zhenyang Cai, Ke Ji, Chuangsen Fang, Ziying Sheng, Xidong Wang, Rongsheng Wang, Hejia Zhang, Shuang Li, Benyou Wang, Hongyuan Zha
分類: cs.AI, cs.CL, cs.LG
原文アブストラクト
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.
関連論文
- 機械間知識誘導LLMエージェントによる汎用放射線治療計画医療AI/LLMエージェント
