EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM Agents

Mikhail Menschikov, Dmitry Evseev, Victoria Dochkina, Ruslan Kostoev, Ilia Perepechkin, Petr Anokhin, Nikita Semenov, Evgeny Burnaev

IEEE Access · 2026 · 14 · 58262-58281

DOI: 10.1109/access.2026.3682941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Mikhail Menschikov und 7 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Research Centers in the field of AI provided by the Ministry of Economic Development of Russian Federation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Personalizing language models by effectively incorporating user interaction history remains a central challenge in the development of adaptive AI systems. While large language models (LLMs), combined with Retrieval-Augmented Generation (RAG), have improved factual accuracy, they often lack structured memory and fail to scale in complex, long-term interactions. To address this, we propose a flexible external memory framework based on a knowledge graph that is constructed and updated automatically by the LLM. Building upon the AriGraph architecture, we introduce a novel hybrid graph design that supports both standard edges and two types of hyper-edges, enabling rich and dynamic semantic and temporal representations. Our framework also supports diverse retrieval mechanisms, including A*, WaterCircles traversal, beam search, and hybrid methods, making it adaptable to different datasets and LLM capacities. We evaluate our system on TriviaQA, HotpotQA, DiaASQ benchmarks and demonstrate that different memory and retrieval configurations yield optimal performance depending on the task. Additionally, we extend the DiaASQ benchmark with temporal annotations and internally contradictory statements, showing that our system remains robust and effective in managing temporal dependencies and context-aware reasoning.

Förderung

  • Research Centers in the field of AI provided by the Ministry of Economic Development of Russian Federation

Zitieren

APA

Menschikov, M., Evseev, D., Dochkina, V., Kostoev, R., Perepechkin, I., Anokhin, P., Semenov, N., & Burnaev, E. (2026). PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM Agents. IEEE Access, 14, 58262-58281. https://doi.org/10.1109/access.2026.3682941

Vancouver

Menschikov M, Evseev D, Dochkina V, Kostoev R, Perepechkin I, Anokhin P, et al. PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM Agents. IEEE Access. 2026;14:58262-58281. doi:10.1109/access.2026.3682941

BibTeX
@article{Menschikov2026,
  author = {Menschikov, Mikhail and Evseev, Dmitry and Dochkina, Victoria and Kostoev, Ruslan and Perepechkin, Ilia and Anokhin, Petr and Semenov, Nikita and Burnaev, Evgeny},
  title = {PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM Agents},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {58262--58281},
  doi = {10.1109/access.2026.3682941}
}
Kostenlos starten →