mlsanityData to 14 Oct 2026

Co-Evolving Structured Knowledge and Reasoning in Language Models

arXiv 2608.26386 ↗First posted 26 Aug 2026cs.CL cs.AI cs.LGcited by 0

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented methods improve factual accuracy by grounding language models in external knowledge, but retrieving over unstructured text often introduces irrelevant context and offers limited control over the retrieved information. Structured knowledge bases offer a more controllable alternative, yet they are expensive to construct and often brittle to reason over. To address these limitations, we propose KBevo: a co-evolving framework that jointly learns to construct a structured knowledge base and reason over it for knowledge-intensive question answering. By optimizing both components end-to-end with QA outcome rewards, our method enables reasoning success to directly improve the quality of the constructed knowledge base. This leads to larger, better-connected knowledge structures with higher answer reachability, while also improving compositional factual reasoning and controllability compared to standard retrieval baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 47 of its 51 references that are in the map. First posted on arXiv 26 Aug 2026.

Builds on

47 of 51 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning21 Jan
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  3. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  4. 2024Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning18 Oct
  5. 2024Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Exploration3 Aug
  6. 2024Improving Multi-hop Logical Reasoning in Knowledge Graphs with Context-Aware Query Representation Learning11 Jun
  7. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 40

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  9. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  10. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  11. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  12. 2022Locating and Editing Factual Associations in GPTcited by 2,691
28 more
  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  2. 2019Language Models as Knowledge Bases?cited by 1,936
  3. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  6. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 982
  7. 2022Toy Models of Superpositioncited by 971
  8. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  9. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  10. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  11. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wildcited by 511
  12. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  13. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 377
  14. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 300
  15. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 286
  16. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  17. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 150
  18. 2023Physics of Language Models: Part 3.2, Knowledge Manipulationcited by 143
  19. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  20. 2024Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Constructioncited by 70
  21. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  22. 2025Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Modelscited by 39
  23. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  24. 2024LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environmentscited by 18
  25. 2025Pretraining with hierarchical memories: separating long-tail and common knowledgecited by 14
  26. 2025Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Needcited by 13
  27. 2025Pre-training Limited Memory Language Models with Internal and External Knowledgecited by 12
  28. 2025Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Modelscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
  2. 2024A Learn-Then-Reason Model Towards Generalization in Knowledge Base Question Answering
  3. 2025Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
  4. 2025KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
  5. 2025Improving Context Fidelity via Native Retrieval-Augmented Reasoning
  6. 2025LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge
  7. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
  8. 2022Structured Knowledge Grounding for Question Answering