SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914455043964928 |
|---|---|
| author | Yang, Bufang Xu, Lilin Li, Yixuan Liu, Kaiwei Jiang, Xiaofan Yan, Zhenyu |
| author_facet | Yang, Bufang Xu, Lilin Li, Yixuan Liu, Kaiwei Jiang, Xiaofan Yan, Zhenyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06204 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams Yang, Bufang Xu, Lilin Li, Yixuan Liu, Kaiwei Jiang, Xiaofan Yan, Zhenyu Computation and Language Artificial Intelligence Human-Computer Interaction 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. |
| title | SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2604.06204 |