Longitudinal clinical reasoning over electronic health records requires tracking evolving physiological measurements, laboratory results, and interventions across extended patient trajectories. Existing LLM-based clinical reasoning systems often rely on repeatedly serializing patient histories or exchanging unconstrained textual agent messages, leading to context drift, unstable reasoning, and growing inference cost over long horizons. We present Vital Trace, a protocol-constrained multi-agent framework for future clinical risk prediction over evolving ICU trajectories. Instead of maintaining unbounded textual histories, Vital Trace uses a compact persistent patient-state memory together with staged reasoning performed by four coordinated agents: a Router, Reasoner, Auditor, and Steward. To support temporally coherent reasoning, we introduce a manually curated Global Protocol containing physiological state-transition rules and a dynamic patient-state representation that tracks hemodynamic, respiratory, renal, metabolic, and inflammatory instability over time. We evaluate Vital Trace on MIMIC-IV and eICU using future vasopressor-support, respiratory-support, renal-support, and deterioration prediction tasks. Results show that structured protocol-constrained reasoning improves temporal consistency, communication stability, calibration, and interpretability compared with free-form multi-agent baselines while achieving strong predictive performance across long ICU trajectories.

翻译：电子健康记录中的纵向临床推理需要追踪患者整个病程中不断演变的生理测量指标、实验室检查结果及干预措施。现有基于大语言模型的临床推理系统往往依赖重复序列化患者病史或交换不受约束的文本代理消息，导致长病程场景下出现上下文漂移、推理不稳定及推理成本递增问题。本文提出Vital Trace——一种面向重症监护室（ICU）轨迹演进的未来临床风险预测协议约束多智能体框架。该框架摒弃无界文本病史维护方式，采用紧凑型持久化患者状态记忆模块，通过四个协同智能体（路由智能体、推理智能体、审计智能体与管家智能体）实施分阶段推理。为实现时间一致性推理，我们引入人工构建的全局协议（包含生理状态转移规则）与动态患者状态表征系统，可跨时间维度追踪血流动力学、呼吸系统、肾脏功能、代谢状态及炎症反应等指标的不稳定性。基于MIMIC-IV与eICU数据集，我们在未来血管活性药物支持、呼吸支持、肾脏支持及病情恶化预测任务中评估了Vital Trace性能。结果表明，与自由格式多智能体基线方法相比，结构化协议约束推理在长ICU轨迹中不仅能提升时间一致性、通信稳定性、校准质量与可解释性，同时保持了优异的预测性能。