# You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures

arXiv: https://arxiv.org/abs/2508.06105 · HTML: https://mlsanity.com/paper/2508.06105/

## Key facts

- Cited by 23 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 23 of its 56 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models](https://mlsanity.com/paper/2410.02355/) (2024)
- [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://mlsanity.com/paper/2402.07630/) (2024)
- [A Survey of Graph Meets Large Language Model: Progress and Future Directions](https://mlsanity.com/paper/2311.12399/) (2023)
- [When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.05690/) (2025)
- [In-depth Analysis of Graph-based RAG in a Unified Framework](https://mlsanity.com/paper/2503.04338/) (2025)
- [SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.08813/) (2025)
- [FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.08938/) (2025)
- [UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI](https://mlsanity.com/paper/2412.20977/) (2024)
- [Entity Alignment with Noisy Annotations from Large Language Models](https://mlsanity.com/paper/2405.16806/) (2024)
- [Empowering GraphRAG with Knowledge Filtering and Integration](https://mlsanity.com/paper/2503.13804/) (2025)
- [EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora](https://mlsanity.com/paper/2506.20963/) (2025)
- [Each Graph is a New Language: Graph Learning with LLMs](https://mlsanity.com/paper/2501.11478/) (2025)
- [LAG: Logic-Augmented Generation from a Cartesian Perspective](https://mlsanity.com/paper/2508.05509/) (2025)
- [Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs](https://mlsanity.com/paper/2506.10508/) (2025)
- [Neuro-Symbolic Entity Alignment via Variational Inference](https://mlsanity.com/paper/2410.04153/) (2024)
- [A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering](https://mlsanity.com/paper/2104.08443/) (2021)
- [Hierarchical Instruction-aware Embodied Visual Tracking](https://mlsanity.com/paper/2505.20710/) (2025)

## Built on by (most cited first, 23 of 23)

- [LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora](https://mlsanity.com/paper/2510.10114/) (2025)
- [LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning](https://mlsanity.com/paper/2511.01448/) (2025)
- [FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning](https://mlsanity.com/paper/2601.03938/) (2026)
- [DeepSurvey-Bench: Evaluating Academic Value of Automatically Generated Scientific Surveys](https://mlsanity.com/paper/2601.15307/) (2026)
- [LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval](https://mlsanity.com/paper/2508.07690/) (2025)
- [Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.12460/) (2025)
- [Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs](https://mlsanity.com/paper/2603.14006/) (2026)
- [ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2605.28093/) (2026)
- [SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search](https://mlsanity.com/paper/2605.29796/) (2026)
- [IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memory](https://mlsanity.com/paper/2602.07525/) (2026)
- [AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.20844/) (2026)
- [Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering](https://mlsanity.com/paper/2606.10921/) (2026)
- [CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAG](https://mlsanity.com/paper/2607.26470/) (2026)
- [MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG](https://mlsanity.com/paper/2608.02195/) (2026)
- [D2F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation](https://mlsanity.com/paper/2608.04444/) (2026)
- [Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering](https://mlsanity.com/paper/2608.13160/) (2026)
- [DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extraction](https://mlsanity.com/paper/2608.22014/) (2026)
- [EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution](https://mlsanity.com/paper/2608.23265/) (2026)
- [A Tree-based RAG Framework for Evidence-Intensive QA via Adaptive Planning and Topology-Aware Evidence Gathering](https://mlsanity.com/paper/2609.04981/) (2026)
- [LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning](https://mlsanity.com/paper/2609.27009/) (2026)
- [Realize What Matters: Principled Context Representation for Large-Scale Reasoning](https://mlsanity.com/paper/2609.27173/) (2026)
- [Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.37661/) (2026)
- [DAGent: Evaluate-then-Grow Planning for Deep Research Agents](https://mlsanity.com/paper/2609.39154/) (2026)

## Abstract (arXiv)

Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving query-relevant contexts from knowledge bases to support LLM reasoning. Recent advances leverage pre-constructed graphs to capture the relational connections among distributed documents, showing remarkable performance in complex tasks. However, existing Graph-based RAG (GraphRAG) methods rely on a costly process to transform the corpus into a graph, introducing overwhelming token cost and update latency. Moreover, real-world queries vary in type and complexity, requiring different logic structures for accurate reasoning. The pre-built graph may not align with these required structures, resulting in ineffective knowledge retrieval. To this end, we propose a Logic-aware Retrieval-Augmented Generation framework (LogicRAG) that dynamically extracts reasoning structures at inference time to guide adaptive retrieval without any pre-built graph. LogicRAG begins by decomposing the input query into a set of subproblems and constructing a directed acyclic graph (DAG) to model the logical dependencies among them. To support coherent multi-step reasoning, LogicRAG then linearizes the graph using topological sort, so that subproblems can be addressed in a logically consistent order. Besides, LogicRAG applies graph pruning to reduce redundant retrieval and uses context pruning to filter irrelevant context, significantly reducing the overall token cost. Extensive experiments demonstrate that LogicRAG achieves both superior performance and efficiency compared to state-of-the-art baselines.