SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams
This addresses the limitation of existing LLM-based personalization methods for users by enabling more accurate and stable persona inference from real-world sensor data, though it is incremental in combining existing techniques with sensor streams.
The paper tackles the problem of inferring comprehensive user personas from everyday behaviors rather than chat histories, by introducing SensorPersona, a system that continuously extracts personas from longitudinal mobile sensor streams, achieving up to 31.4% higher recall in persona extraction and an 85.7% win rate in persona-aware agent responses.
Personalization is essential for Large Language Model (LLM)-based agents to adapt to users' preferences and improve response quality and task performance. However, most existing approaches infer personas from chat histories, which capture only self-disclosed information rather than users' everyday behaviors in the physical world, limiting the ability to infer comprehensive user personas. In this work, we introduce SensorPersona, an LLM-empowered system that continuously infers stable user personas from multimodal longitudinal sensor streams unobtrusively collected from users' mobile devices. SensorPersona first performs person-oriented context encoding on continuous sensor streams to enrich the semantics of sensor contexts. It then employs hierarchical persona reasoning that integrates intra- and inter-episode reasoning to infer personas spanning physical patterns, psychosocial traits, and life experiences. Finally, it employs clustering-aware incremental verification and temporal evidence-aware updating to adapt to evolving personas. We evaluate SensorPersona on a self-collected dataset containing 1,580 hours of sensor data from 20 participants, collected over up to 3 months across 17 cities on 3 continents. Results show that SensorPersona achieves up to 31.4% higher recall in persona extraction, an 85.7% win rate in persona-aware agent responses, and notable improvements in user satisfaction compared to state-of-the-art baselines.