{"ID":2874077,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.04752","arxiv_id":"2509.04752","title":"SePA: A Search-enhanced Predictive Agent for Personalized Health Coaching","abstract":"This paper introduces SePA (Search-enhanced Predictive AI Agent), a novel LLM health coaching system that integrates personalized machine learning and retrieval-augmented generation to deliver adaptive, evidence-based guidance. SePA combines: (1) Individualized models predicting daily stress, soreness, and injury risk from wearable sensor data (28 users, 1260 data points); and (2) A retrieval module that grounds LLM-generated feedback in expert-vetted web content to ensure contextual relevance and reliability. Our predictive models, evaluated with rolling-origin cross-validation and group k-fold cross-validation show that personalized models outperform generalized baselines. In a pilot expert study (n=4), SePA's retrieval-based advice was preferred over a non-retrieval baseline, yielding meaningful practical effect (Cliff's $δ$=0.3, p=0.05). We also quantify latency performance trade-offs between response quality and speed, offering a transparent blueprint for next-generation, trustworthy personal health informatics systems.","short_abstract":"This paper introduces SePA (Search-enhanced Predictive AI Agent), a novel LLM health coaching system that integrates personalized machine learning and retrieval-augmented generation to deliver adaptive, evidence-based guidance. SePA combines: (1) Individualized models predicting daily stress, soreness, and injury risk...","url_abs":"https://arxiv.org/abs/2509.04752","url_pdf":"https://arxiv.org/pdf/2509.04752v1","authors":"[\"Melik Ozolcer\",\"Sang Won Bae\"]","published":"2025-09-05T02:07:36Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.AI\",\"cs.LG\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false}