PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM

TL;DR

This paper introduces PersonaAgent with GraphRAG, a framework that creates personalized, community-aware knowledge graphs to enhance large language models for tailored user interactions, improving task performance significantly.

Contribution

The paper presents a novel framework combining knowledge graphs and community detection to generate personalized prompts for LLMs, enabling more consistent and community-aware AI agents.

Findings

Improves news categorization F1 by 11.1%

Enhances movie tagging F1 by 56.1%

Reduces product rating MAE by 10.4%

Abstract

We propose a novel framework for persona-based language model system, motivated by the need for personalized AI agents that adapt to individual user preferences. In our approach, the agent embodies the user's "persona" (e.g. user profile or taste) and is powered by a large language model (LLM). To enable the agent to leverage rich contextual information, we introduce a Knowledge-Graph-enhanced Retrieval-Augmented Generation (Graph RAG) mechanism that constructs an LLM-derived graph index of relevant documents and summarizes communities of related information. Our framework generates personalized prompts by combining: (1) a summary of the user's historical behaviors and preferences extracted from the knowledge graph, and (2) relevant global interaction patterns identified through graph-based community detection. This dynamic prompt engineering approach allows the agent to maintain consistent persona-aligned behaviors while benefiting from collective knowledge. On the LaMP benchmark, our method improves news categorization F1 by 11.1%, movie tagging F1 by 56.1%, and reduces product rating MAE by 10.4% over prior methods. Our code is available at https://anonymous.4open.science/r/PersonaAgentwGraphRAG-DE6F