智能体增强型异质图检索增强生成（RAG）在学术问答中的应用
Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering
浏览论文内容
中文总结 AI 辅助
该研究针对学术问答场景下现有RAG系统的三类局限，提出智能体增强型异质图RAG方法，通过三类智能体实现自适应检索、证据评估与图事实验证，实验显示其性能优于多种基线方法。
中文摘要 AI 辅助
学术问答需要对异质学术图进行推理，查询范围从简单的属性查找到作者-论文- venue结构的多跳推理。现有的检索增强生成（RAG）系统在该场景下存在三个局限：（1）固定的检索策略无法适配不同查询复杂度；（2）缺乏充分性评估导致证据不完整或不对齐；（3）缺乏对图事实的结构化验证。为解决这些问题，我们提出智能体异质图RAG方法，将RAG流程的三个核心阶段转化为显式的智能体决策步骤：查询感知的检索智能体分析查询类型并选择合适的图遍历策略；充分性感知的重排序智能体评估证据完整性并自适应扩展检索到的子图；基于图的验证智能体在最终确定答案前检查实体、关系和属性的正确性。在由OpenAlex和DBLP构建的异质图上开展的实验表明，我们的方法在性能上持续优于强大的大语言模型（LLM）、图增强型RAG以及基于智能体的基线方法。
英文摘要
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.
发表机构
- University of Technology Sydney（悉尼科技大学）
- University of Texas at Austin（德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。
