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.

翻译：图检索增强生成通过将语料组织为知识图谱并沿着关系结构路由证据，增强了多跳问答能力。然而，实际部署面临两个持续性瓶颈：（i）混合难度工作负载中，统一检索策略要么在简单查询上浪费成本，要么在复杂多跳任务中失效；（ii）图抽象导致的提取损失，使得仅存于源文本的细粒度限定词被遗漏。我们提出A2RAG——一种面向成本感知与可靠推理的自适应智能图检索框架。该框架将验证证据充分性并在必要时触发精准优化的自适应控制器，与逐步提升检索力度并将图信号映射回原始文本以应对提取损失和不完整图的智能检索器相结合。在HotpotQA和2WikiMultiHopQA上的实验表明，A2RAG在Recall@2指标上取得+9.9/+11.8的绝对提升，同时相较于迭代多跳基线方法，令牌消耗与端到端延迟降低约50%。