动态调整检索策略，让模型更省钱、更可靠地回答复杂问题。
A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning
- 根据问题难度自动调节检索强度，避免资源浪费或遗漏信息。
- 在两个数据集上召回率提升超过9.9%，同时减少50%的耗时和令牌消耗。
- 适合追求高效准确推理的应用，尤其适用于信息不完整场景。
图检索增强生成（Graph-RAG）通过将文档组织为知识图谱，并利用关系结构路由证据，提升多跳问答能力。但实际部署面临两大瓶颈：(i) 混合难度任务中，统一检索策略要么对简单问题浪费成本，要么在复杂多跳问题上失败；(ii) 抽取损失，图抽象过程会丢失源文本中的细粒度限定词。本文提出A2RAG，一种自适应且具有代理特性的Graph-RAG框架，实现成本敏感与可靠的推理。A2RAG结合自适应控制器，仅在必要时触发精准化修正；并采用代理式检索器，逐步升级检索力度，同时将图信号映射回原文出处，以应对抽取损失和图谱不完整问题。在HotpotQA和2WikiMultiHopQA上的实验表明，A2RAG在Recall@2上分别取得+9.9/+11.8的绝对提升，同时相比迭代多跳基线，令牌消耗和端到端延迟降低约50%。
原文摘要 · Abstract (English)
Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two persistent bottlenecks: (i) mixed-difficulty workloads where one-size-fits-all retrieval either wastes cost on easy queries or fails on hard multihop cases, and (ii) extraction loss, where graph abstraction omits fine-grained qualifiers that remain only in source text. We present A2RAG, an adaptive-and-agentic GraphRAG framework for cost-aware and reliable reasoning. A2RAG couples an adaptive controller that verifies evidence sufficiency and triggers targeted refinement only when necessary, with an agentic retriever that progressively escalates retrieval effort and maps graph signals back to provenance text to remain robust under extraction loss and incomplete graphs. Experiments on HotpotQA and 2WikiMultiHopQA demonstrate that A2RAG achieves +9.9/+11.8 absolute gains in Recall@2, while cutting token consumption and end-to-end latency by about 50% relative to iterative multihop baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。