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

arXiv: https://arxiv.org/abs/2605.30237 · HTML: https://mlsanity.com/paper/2605.30237/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 15 of 15)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents](https://mlsanity.com/paper/2506.00641/) (2025)
- [HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases](https://mlsanity.com/paper/2412.16311/) (2024)
- [Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval](https://mlsanity.com/paper/2410.13765/) (2024)
- [Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis](https://mlsanity.com/paper/2603.16877/) (2026)
- [Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases](https://mlsanity.com/paper/2502.20317/) (2025)
- [AutoPCR: Automated Phenotype Concept Recognition by Prompting](https://mlsanity.com/paper/2507.19315/) (2025)
- [DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition](https://mlsanity.com/paper/2409.11022/) (2024)
- [Graphical Reasoning: LLM-based Semi-Open Relation Extraction](https://mlsanity.com/paper/2405.00216/) (2024)
- [Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge](https://mlsanity.com/paper/2505.09246/) (2025)
- [HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs](https://mlsanity.com/paper/2404.00816/) (2024)
- [SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition](https://mlsanity.com/paper/2604.20146/) (2026)

## Built on by (most cited first, 7 of 7)

- [MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures](https://mlsanity.com/paper/2608.07556/) (2026)
- [Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs](https://mlsanity.com/paper/2606.25758/) (2026)
- [When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost](https://mlsanity.com/paper/2607.24010/) (2026)
- [Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions](https://mlsanity.com/paper/2607.21635/) (2026)
- [Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval](https://mlsanity.com/paper/2608.00183/) (2026)
- [Toward Workflow-Aware Benchmarking for Healthcare NLP Agents](https://mlsanity.com/paper/2609.00296/) (2026)
- [Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve](https://mlsanity.com/paper/2610.18616/) (2026)

## Abstract (arXiv)

Retrieval over semi-structured knowledge bases (SKBs) must handle both textual descriptions and relational constraints. Text-based retrievers capture the overall semantics of a query but struggle with multi-hop relations, whereas graph-based retrievers follow relational paths precisely but miss the broader meaning. We propose GRASP, a hybrid retriever that learns to fuse the two. A small LLM planner translates the query into an executable graph plan in a single call, its graph ranking is fused with a text ranking, and a fine-tuned reranker reorders the fused candidates. Instead of training the planner to be accurate on its own, we optimize it with reinforcement learning to maximize the gain its graph ranking brings to the fused ranking. On three STaRK benchmarks, GRASP achieves the best results on all metrics, improving the average Hit@1 by 18.6 points over the strongest baseline, while taking only 2.47 seconds per query.