mlsanityData to 7 Oct 2026

Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking

arXiv 2508.02435 ↗First posted 4 Aug 2025cs.IRcited by 6

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency. Multi-round RAG approaches achieve strong reasoning but incur excessive LLM calls and token costs, while Graph RAG methods suffer from computationally expensive, error-prone graph construction and retrieval redundancy. To address these challenges, we propose T2RAG, a novel framework that operates on a simple, graph-free knowledge base of atomic triplets. T2RAG leverages an LLM to decompose questions into searchable triplets with placeholders, which it then iteratively resolves by retrieving evidence from the triplet database. Empirical results show that T2RAG significantly outperforms state-of-the-art multi-round and Graph RAG methods, achieving an average performance gain of up to 11% across six datasets while reducing retrieval costs by up to 45%. Our code is available at https://github.com/rockcor/T2RAG

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 78 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

34 of 78 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024SiReRAG: Indexing Similar and Related Information for Multihop Reasoning9 Dec
  2. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  4. 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Model9 Oct
  5. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning2 Oct
  6. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph15 Jul

Other references · 28

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  3. 2024A Survey on LLM-as-a-Judgecited by 1,384
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  5. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  6. 2024The Faiss librarycited by 370
  7. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  8. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  9. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  10. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
  11. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  12. 2023Query2doc: Query Expansion with Large Language Modelscited by 146
16 more
  1. 2025HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representationcited by 68
  2. 2023Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answeringcited by 64
  3. 2020UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answeringcited by 61
  4. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  5. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 46
  6. 2025In-depth Analysis of Graph-based RAG in a Unified Frameworkcited by 45
  7. 2023End-to-End Beam Retrieval for Multi-Hop Question Answeringcited by 35
  8. 2025A Comprehensive Survey of Machine Unlearning Techniques for Large Language Modelscited by 30
  9. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 30
  10. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
  11. 2024Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentationcited by 24
  12. 2023Direct Fact Retrieval from Knowledge Graphs without Entity Linkingcited by 22
  13. 2024GeAR: Graph-enhanced Agent for Retrieval-augmented Generationcited by 17
  14. 2022ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphscited by 16
  15. 2025EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corporacited by 14
  16. 2025Scalable Graph Condensation with Evolving Capabilitiescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examplescited by 8
  2. 2026STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learningcited by 7
  3. 2026G2-Reader: Dual Evolving Graphs for Multimodal Document QAcited by 1
  4. 2026NuggetIndex: Governed Atomic Retrieval for Maintainable RAGcited by 1
  5. 2026NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosiscited by 1
  6. 2026HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  2. 2026Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
  3. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  4. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
  5. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  6. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  7. 2025Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation
  8. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG