GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases

Yicheng Tao; Yiqun Wang; Xiangchen Song; Xin Luo; Kai Liu; Jie Liu

cs.IRMay 28, 2026

GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases

Authors: Yicheng Tao, Yiqun Wang, Xiangchen Song, Xin Luo, Kai Liu, Jie Liu

Organizations: Department of Electrical Engineering and Computer Science, University of Michigan · Department of Computational Medicine and Bioinformatics, University of Michigan

Abstract

Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product search, academic paper search, and precision-medicine inquiries. Existing hybrid retrieval systems on SKBs either use the graph only for query expansion, mix textual and structural branches under a global weighting, or rely on fine-tuned graph-traversal generators. We present GRASP, a three-stage SKB retrieval framework unifying plan-based graph retrieval, plan-conditioned fusion with a dense retriever, and a fine-tuned reranker over the fused candidates. GRASP substantially advances the state of the art on every metric across the three STaRK benchmarks, lifting average Hit@1 from 62.0 to 73.9. Ablation and sensitivity studies further confirm the effectiveness and robustness of GRASP.

Explore similar work

SeedER: Seed-and-Expand Retrieval from Knowledge Graphs
May 22, 2026Hamed Shirzad, Frederik Wenkel, Dominique Beaini +2Graph-Based Retrieval Knowledge Graphs
Comparative Approaches to Agent Retrieval over Large Skill Libraries
Aug 6, 2026Indivara Kolluru, Nathan SportsmanReranking Knowledge Graphs
Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering
May 26, 2026Mateusz Czyżnikiewicz, Ryszard Tuora, Adam Kozakiewicz +6Knowledge Graphs Symbol-

May 22, 2026 · cs.LGJ/K move · Enter open · S save

SeedER: Seed-and-Expand Retrieval from Knowledge Graphs

Hamed Shirzad, Frederik Wenkel, Dominique Beaini, Danica J. Sutherland+1

Valence Labs, Montréal, QC, Canada · Recursion, Salt Lake City, UT, USA · University of British Columbia, Department of Computer Science, Vancouver, BC, Canada

Knowledge graphs (KGs) offer a rich representation for relational knowledge, but their irregular structure makes retrieval challenging: ego-graph expansion grows rapidly, and dense embedding methods struggle with multi-hop compositional queries. Existing agent-based graph exploration approaches, while expressive, are often too expensive for large-scale retrieval. We introduce SeedER (Seed-and-Expand Retrieval), a retrieval framework that explicitly leverages KG structure through iterative, low-cost expansion. SeedER first seeds a compact set of core nodes using lightweight dense and entity-based retrieval, then selectively expands this set via a learned graph-aware policy trained with reinforcement learning. This design decomposes global reasoning into reusable local decisions, enabling efficient discovery of query-relevant nodes while tightly controlling expansion cost. We show theoretical limitations of dense retrieval on compositional graph queries, and establish advantages of SeedER from both compositional generalization and graph-constrained submodular optimization perspectives. Empirically, SeedER substantially improves recall with compact candidate sets over strong dense and graph-augmented baselines, making it an effective first-stage retriever for knowledge-intensive reasoning systems.

Graph-Based Retrieval Knowledge Graphs Expansions Complex Networks

Open paper Ask about it PDF

Abstract

Explore similar work

SeedER: Seed-and-Expand Retrieval from Knowledge Graphs

Comparative Approaches to Agent Retrieval over Large Skill Libraries

Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering