A longitudinal health agent framework
Georgianna, Lin, Rencong Jiang, Noémie Elhadad, Xuhai "Orson" Xu
TLDR
This paper proposes a multi-layer framework and architecture for AI agents to support longitudinal health tasks, ensuring adaptation, coherence, and continuity over time.
Key contributions
- Defines what it means to orchestrate longitudinal health interactions with AI agents.
- Proposes a multi-layer framework and agent architecture for long-term health support.
- Operationalizes adaptation, coherence, continuity, and agency across repeated interactions.
- Shows how agents maintain engagement, adapt goals, and support personalized decision-making.
Why it matters
Current AI agents struggle with long-term health tasks like symptom management and behavior change. This paper introduces a robust framework and architecture to enable AI agents to provide continuous, adaptive, and personalized support over time, improving effectiveness and safety in health trajectories.
Original Abstract
Although artificial intelligence (AI) agents are increasingly proposed to support potentially longitudinal health tasks, such as symptom management, behavior change, and patient support, most current implementations fall short of facilitating user intent and fostering accountability. This contrasts with prior work on supporting longitudinal needs, where follow-up, coherent reasoning, and sustained alignment with individuals' goals are critical for both effectiveness and safety. In this paper, we draw on established clinical and personal health informatics frameworks to define what it would mean to orchestrate longitudinal health interactions with AI agents. We propose a multi-layer framework and corresponding agent architecture that operationalizes adaptation, coherence, continuity, and agency across repeated interactions. Through representative use cases, we demonstrate how longitudinal agents can maintain meaningful engagement, adapt to evolving goals, and support safe, personalized decision-making over time. Our findings underscore both the promise and the complexity of designing systems capable of supporting health trajectories beyond isolated interactions, and we offer guidance for future research and development in multi-session, user-centered health AI.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.