Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (37) · 31229-31237
DOI: 10.1609/aaai.v40i37.40385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhaopei Huang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
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 H2Memory, 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.
Zitieren
APA
Huang, Z., Dai, Q., Wu, G., Wu, X., Li, X., Ge, T., Wang, W., & Jin, Q. (2026). Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(37), 31229-31237. https://doi.org/10.1609/aaai.v40i37.40385
Vancouver
Huang Z, Dai Q, Wu G, Wu X, Li X, Ge T, et al. Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(37):31229-31237. doi:10.1609/aaai.v40i37.40385
BibTeX
@article{Huang2026,
author = {Huang, Zhaopei and Dai, Qifeng and Wu, Guozheng and Wu, Xiaopeng and Li, Xubin and Ge, Tiezheng and Wang, Wenxuan and Jin, Qin},
title = {Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {37},
pages = {31229--31237},
doi = {10.1609/aaai.v40i37.40385}
}
EUVIMED