Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering

2026-09-01

AI Summary

本文针对学术问答中异构图推理问题，提出了一种基于代理的异构图RAG方法，通过查询感知检索、充分性评估和图验证三个代理步骤来改进现有系统的不足。

Abstract

Academic question answering requires reasoning over heterogeneous scholarly graphs, where queries range from simple attribute lookups to multi-hop inference across author--paper--venue structures. Existing retrieval-augmented generation (RAG) systems struggle in this setting due to three limitations: (1) fixed retrieval strategies that do not adapt to varying query complexity, (2) the absence of sufficiency evaluation leading to incomplete or misaligned evidence, and (3) a lack of structured verification against graph facts. To address these issues, we propose an agentic heterogeneous graph RAG method that transforms the three core stages of the RAG pipeline into explicit agentic decision steps. A query-aware retrieval agent analyzes query type and selects an appropriate graph traversal strategy; a sufficiency-aware reranking agent assesses evidence completeness and adaptively expands the retrieved subgraph; and a graph-grounded verification agent checks entity, relation, and attribute correctness before finalizing the answer. Experiments on heterogeneous graphs constructed from OpenAlex and DBLP suggest that our method consistently outperforms strong LLM, graph-augmented RAG, and agent-based baselines.

Problem

• heterogeneous graph
• retrieval-augmented generation
• query complexity
• sufficiency evaluation
• structured verification

Innovation

• agentic heterogeneous graph RAG
• query-aware retrieval agent
• sufficiency-aware reranking agent
• graph-grounded verification agent