ArcRAG：推理时诱导查询本地接口，实现跨图构建的知识图谱检索
ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs
一篇 arXiv 新论文 ArcRAG，检索不绑定建图方式，在 MuSiQue、HotpotQA、TriviaQA 上换图构建照样能用，做 GraphRAG 的可以看看。
arXiv 论文提出 ArcRAG，在推理时根据问题命中的实体诱导查询本地图接口（节点标签、关系描述符、属性键），规划多跳遍历并生成 Cypher 执行和修复。实验把 MuSiQue、HotpotQA、TriviaQA 三个语料各建成 schema 引导图和开放信息抽取图两种构建方式，检索器配置在两者间保持固定。结果显示检索无需与图构建共同设计，跨构建方式依然有效，但构建方式仍影响绝对准确率。论文还与以自身构建流程定制的既有 GraphRAG 系统结果做了对比。
ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs
Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-construction portability: whether one retrieval procedure, with no construction-specific schema, relation names, or retuning, stays effective when the graph is built differently. We introduce ArcRAG, which induces a query-local graph interface at inference time (the node labels, relation descriptors, and property keys reachable from the entities a question names), plans multi-hop traversals against it, and executes and repairs them as Cypher. We build each of the MuSiQue, HotpotQA, and TriviaQA corpora as a schema-guided graph (typed nodes, a closed relation set, source provenance) and as an open-information-extraction graph (untyped nodes, free-text relations), with the retriever's configuration fixed across them. We compare against a construction-agnostic Direct-Cypher agent, ablate each stage across retry and pass budgets on both graph families, and compare with results reported for prior GraphRAG systems, most of which design retrieval together with their own graph construction. Across the two constructions, we find that retrieval need not be co-designed with the graph: query-time interface induction keeps a construction-agnostic retriever effective when the construction changes, although construction still shapes absolute accuracy.