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

Abstract

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

Workflow Status

Review status

pending

Role

unreviewed

Read priority

now

Vote

Not set.

Saved

no

Collections

Not filed yet.

Next action

Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

Similar Papers

BibTeX

@misc{menschikov2026personalai,
  title = {PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents},
  author = {Mikhail Menschikov and Dmitry Evseev and Victoria Dochkina and Ruslan Kostoev and Ilia Perepechkin and Petr Anokhin and Nikita Semenov and Evgeny Burnaev},
  year = {2026},
  abstract = {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},
  url = {https://huggingface.co/papers/2506.17001},
  keywords = {large language models, Retrieval-Augmented Generation, knowledge graph, external memory framework, AriGraph architecture, hyper-edges, A* search, WaterCircles traversal, beam search, temporal dependencies, context-aware reasoning, huggingface daily},
  eprint = {2506.17001},
  archiveprefix = {arXiv},
}

Metadata

{}