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

2025-11-21 · Siqi Liang, Yudi Zhang, Yue Guo arxiv

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

📄 PDF Abstract BibTeX arXiv:2511.17467

Code (0)

등록된 구현이 없습니다.

Tasks

Community Detection Prompt Engineering Knowledge Graphs

When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation

2025-06-06 · Zhishang Xiang, Chuanjie Wu, Qinggang Zhang, Shengyuan Chen 외

Graph retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) with external knowledge. It leverages graphs to model the hierarchical structure between speci…

RAG Retrieval Retrieval-augmented Generation

Core-based Hierarchies for Efficient GraphRAG

2026-03-05 · Jakir Hossain, Ahmet Erdem Sarıyüce arxiv

Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge. However, existing vector-based methods often fail on global sensemaking tasks that require reasoning across many do…

Community Detection Answer Generation Knowledge Graphs

Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration

2026-01-16 · Yuejie Li, Ke Yang, Tao Wang, Bolin Chen 외 arxiv

Graph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often challenged by navigating lar…

Reinforcement Learning Natural Questions

Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs

2026-02-03 · Su Dong, Qinggang Zhang, Yilin Xiao, Shengyuan Chen 외 arxiv

Large language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge. While Retrieval-Augmented Generation (RAG) addresses this by integrating external corpor…

Knowledge Graphs

OMD-GraphRAG: Enhancing GraphRAG with Ontology-Guided Extraction, Multi-Dimensional Clustering and Dual-Channel Fusion

2026-03-26 · Jie Wang, Honghua Huang, Xi Ge, Jianhui Su 외 arxiv

Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While existing GraphRAG frameworks have made progress in structural knowledge orga…