HealthFlow is presented, a multi-agent framework that converts prior EHR analyses into structured, governed experience for planning under dataset-specific and methodological constraints and consistently outperforms strong baselines in generating valid clinical artifacts and completing complex EHR analysis pipelines.
Ying-Hao Zhu, Zi-Xiang Wang, Yi-Fan Qi et al.· npj Digital Medicine· 1 citation
StreamMind is introduced, a two-tier architecture that assigns latency-critical interaction and proactive monitoring to independently scheduled frontend workers, while backend workers asynchronously construct persistent multimodal memory and perform historical recall and external search.
Xichen Zhang, Guankai Li, Yinghao Zhu et al.· 1 citation
A diagnostic framework for AI agent behavior: layer attribution is proposed, which clarifies three consequences: surrogate validity is a model-task-layer relation, human-AI divergence provides diagnostic evidence, and governance requires source attribution before intervention.