Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918218621255680 |
|---|---|
| author | Huang, Zhaopei Dai, Qifeng Wu, Guozheng Wu, Xiaopeng Chen, Kehan Yu, Chuan Li, Xubin Ge, Tiezheng Wang, Wenxuan Jin, Qin |
| author_facet | Huang, Zhaopei Dai, Qifeng Wu, Guozheng Wu, Xiaopeng Chen, Kehan Yu, Chuan Li, Xubin Ge, Tiezheng Wang, Wenxuan Jin, Qin |
| contents | With the rise of smart personal devices, service-oriented human-agent interactions have become increasingly prevalent. This trend highlights the need for personalized dialogue assistants that can understand user-specific traits to accurately interpret requirements and tailor responses to individual preferences. However, existing approaches often overlook the complexities of long-term interactions and fail to capture users' subjective characteristics. To address these gaps, we present PAL-Bench, a new benchmark designed to evaluate the personalization capabilities of service-oriented assistants in long-term user-agent interactions. In the absence of available real-world data, we develop a multi-step LLM-based synthesis pipeline, which is further verified and refined by human annotators. This process yields PAL-Set, the first Chinese dataset comprising multi-session user logs and dialogue histories, which serves as the foundation for PAL-Bench. Furthermore, to improve personalized service-oriented interactions, we propose H$^2$Memory, a hierarchical and heterogeneous memory framework that incorporates retrieval-augmented generation to improve personalized response generation. Comprehensive experiments on both our PAL-Bench and an external dataset demonstrate the effectiveness of the proposed memory framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13410 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction Huang, Zhaopei Dai, Qifeng Wu, Guozheng Wu, Xiaopeng Chen, Kehan Yu, Chuan Li, Xubin Ge, Tiezheng Wang, Wenxuan Jin, Qin Computation and Language With the rise of smart personal devices, service-oriented human-agent interactions have become increasingly prevalent. This trend highlights the need for personalized dialogue assistants that can understand user-specific traits to accurately interpret requirements and tailor responses to individual preferences. However, existing approaches often overlook the complexities of long-term interactions and fail to capture users' subjective characteristics. To address these gaps, we present PAL-Bench, a new benchmark designed to evaluate the personalization capabilities of service-oriented assistants in long-term user-agent interactions. In the absence of available real-world data, we develop a multi-step LLM-based synthesis pipeline, which is further verified and refined by human annotators. This process yields PAL-Set, the first Chinese dataset comprising multi-session user logs and dialogue histories, which serves as the foundation for PAL-Bench. Furthermore, to improve personalized service-oriented interactions, we propose H$^2$Memory, a hierarchical and heterogeneous memory framework that incorporates retrieval-augmented generation to improve personalized response generation. Comprehensive experiments on both our PAL-Bench and an external dataset demonstrate the effectiveness of the proposed memory framework. |
| title | Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.13410 |