# SePA: A Search-enhanced Predictive Agent for Personalized Health Coaching

arXiv: https://arxiv.org/abs/2509.04752 · HTML: https://mlsanity.com/paper/2509.04752/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Placed in

- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 6 of 6)

- [Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data](https://mlsanity.com/paper/2401.06866/) (2024)
- [GPTCoach: Towards LLM-Based Physical Activity Coaching](https://mlsanity.com/paper/2405.06061/) (2024)
- [Towards a Personal Health Large Language Model](https://mlsanity.com/paper/2406.06474/) (2024)
- [PhysioLLM: Supporting Personalized Health Insights with Wearables and Large Language Models](https://mlsanity.com/paper/2406.19283/) (2024)
- [Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Diabetes Patients](https://mlsanity.com/paper/2402.10153/) (2024)
- [Predictive modelling of training loads and injury in Australian football](https://mlsanity.com/paper/1706.04336/) (2017)

## Built on by (most cited first, 1 of 1)

- [Offline Policy Evaluation of Multi-Turn LLM Health Coaching with Real Users](https://mlsanity.com/paper/2510.17173/) (2025)

## Abstract (arXiv)

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.