原文：ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs
作者：Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, Stefano Pasquali
来源：arXiv cs.AI（人工智能）
正文
Computer Science > Computation and Language
arXiv:2611.06481v1 (cs)
[Submitted on 4 Nov 2026]
Title:ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs
Authors:Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, Stefano Pasquali
View a PDF of the paper titled ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs, by Jyotin Goel and 4 other authors
View PDF
HTML (experimental)
Abstract: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.
Comments:
Preprint
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
Cite as:
arXiv:2611.06481 [cs.CL]
(or
arXiv:2611.06481v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2611.06481
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
主题
自然语言处理 · 人工智能 · 信息检索
由「前沿雷达」于 2026-11-04 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。
评论
加载中…