mlsanityData to 14 Oct 2026

Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning

arXiv 2503.05193 ↗First posted 7 Mar 2025cs.CLcited by 10

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Large language models (LLMs) have achieved remarkable performance on knowledge graph question answering (KGQA) tasks by planning and interacting with knowledge graphs. However, existing methods often confuse tool utilization with knowledge reasoning, harming readability of model outputs and giving rise to hallucinatory tool invocations, which hinder the advancement of KGQA. To address this issue, we propose Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning (MemQ) to decouple LLM from tool invocation tasks using LLM-built query memory. By establishing a memory module with explicit descriptions of query statements, the proposed MemQ facilitates the KGQA process with natural language reasoning and memory-augmented query reconstruction. Meanwhile, we design an effective and readable reasoning to enhance the LLM's reasoning capability in KGQA. Experimental results that MemQ achieves state-of-the-art performance on widely used benchmarks WebQSP and CWQ.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 13 of its 37 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

13 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024LLM-based Discriminative Reasoning for Knowledge Graph Question Answering17 Dec
  2. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph17 Feb
  3. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph2 Dec

Other references · 10

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2024Qwen2 Technical Reportcited by 2,120
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  5. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 140
  6. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 102
  7. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  8. 2024Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answeringcited by 60
  9. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  10. 2024Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoningcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 4.

10 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2024Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
  2. 2025RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
  3. 2026A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering
  4. 2025Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching
  5. 2023KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
  6. 2026RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
  7. 2026MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
  8. 2024Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data