Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data

ArXi:2605.18763v1 Announce Type: cross Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are long-term, multimodal, and highly personalized. A key challenge is context selection: providing insufficient context limits reasoning, while including all available data leads to inefficiency and degraded generation quality. We propose Wearable As Graph (WAG), a graph-based context retrieval framework that enables query-adaptive reasoning over wearable data with LLMs.