mlsanityData to 14 Oct 2026

AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction

arXiv 2510.15339 ↗First posted 17 Oct 2025cs.CL cs.AIcited by 7

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

also in 1 more
Abstract (arXiv)

Building effective knowledge graphs (KGs) for Retrieval-Augmented Generation (RAG) is pivotal for advancing question answering (QA) systems. However, its effectiveness is hindered by a fundamental disconnect: the knowledge graph (KG) construction process is decoupled from its downstream application, yielding suboptimal graph structures. To bridge this gap, we introduce AutoGraph-R1, the first framework to directly optimize KG construction for task performance using Reinforcement Learning (RL). AutoGraph-R1 trains an LLM constructor by framing graph generation as a policy learning problem, where the reward is derived from the graph's functional utility in a RAG pipeline. We design two novel, task-aware reward functions, one for graphs as knowledge carriers and another as knowledge indices. Across multiple QA benchmarks, AutoGraph-R1 consistently enables graph RAG methods to achieve significant performance gains over using task-agnostic baseline graphs. Our work shows it is possible to close the loop between construction and application, shifting the paradigm from building intrinsically ``good'' graphs to building demonstrably ``useful'' ones.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 68 of its 82 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

68 of 82 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning29 Jul
  2. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation6 Jun
  3. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights17 Feb
  4. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models21 Jan
  5. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation28 Oct
  6. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  7. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation15 Jul
  8. 2024Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning27 May
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  10. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering12 Feb

Other references · 58

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2024Qwen2.5 Technical Reportcited by 4,942
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  9. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  10. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  11. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  12. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
38 more
  1. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  2. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  3. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  4. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  7. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 686
  8. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 526
  9. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Modelcited by 461
  10. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  11. 2023A Survey of Reinforcement Learning from Human Feedbackcited by 264
  12. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  13. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  14. 2023A Study of Generative Large Language Model for Medical Research and Healthcarecited by 163
  15. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  16. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  17. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  18. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generationcited by 90
  19. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 71
  20. 2025DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learningcited by 66
  21. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 65
  22. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  23. 2025KGGen: Extracting Knowledge Graphs from Plain Text with Language Modelscited by 49
  24. 2023PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMscited by 44
  25. 2024GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Modelscited by 43
  26. 2025s3: You Don't Need That Much Data to Train a Search Agent via RLcited by 42
  27. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  28. 2024GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Modelcited by 40
  29. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 31
  30. 2024Knowledge Graph-Enhanced Large Language Models via Path Selectioncited by 28
  31. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  32. 2024Entity Alignment with Noisy Annotations from Large Language Modelscited by 22
  33. 2023Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generationcited by 19
  34. 2023B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesiscited by 17
  35. 2021ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Modelscited by 16
  36. 2025Top Ten Challenges Towards Agentic Neural Graph Databasescited by 13
  37. 2022Contrastive Knowledge Graph Error Detectioncited by 11
  38. 2024iText2KG: Incremental Knowledge Graphs Construction Using Large Language Modelscited by 11

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  2. 2026SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memorycited by 2
  3. 2026DeepRefine: Agentic Knowledge Refinement via Reinforcement Learningcited by 1
  4. 2026MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generationcited by 1
  5. 2026TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluationcited by 0
  6. 2026HyGRL: Adaptive Hybrid Graph Reasoning for Multi-Entity Questionscited by 0
  7. 2026MMKG-R1: Constructing Multimodal Knowledge Graphs via Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
  2. 2025Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs
  3. 2026Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
  4. 2026HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG
  5. 2026Search-on-Graph-R1: Training Large Language Models to Search Knowledge Graphs with Reinforcement Learning
  6. 2026GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning
  7. 2025TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
  8. 2026RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering