mlsanityData to 14 Oct 2026

KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation

arXiv 2506.17728 ↗First posted 21 Jun 2025cs.CL cs.AIcited by 2

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

Abstract (arXiv)

In this paper, we introduce KAG-Thinker, which upgrade KAG to a multi-turn interactive thinking and deep reasoning framework powered by a dedicated parameter-light large language model (LLM). Our approach constructs a structured thinking process for solving complex problems, enhancing the the logical coherence and contextual consistency of the reasoning process in question-answering (Q&A) tasks on domain-specific knowledge bases (KBs) within LLMs. Following the Logical Form guided retrieval and reasoning technology route of KAG, this framework first decomposes complex questions into independently solvable sub-problems (which are also referred to as logical forms) through breadth decomposition. Each such logical form is represented in two equivalent forms-natural language and logical function-and subsequently classified as either a Knowledge Retrieval or Reasoning Analysis task. Dependencies and parameter passing between these tasks are explicitly modeled via logical function interfaces. In the solving process, the Retrieval function performs retrieval tasks. It retrieves one-hop structured and unstructured information of specified knowledge unit. While the Math and Deduce functions are used to perform reasoning analysis tasks. Secondly, it is worth noting that, in the Knowledge Retrieval sub-problem tasks, LLMs and external knowledge sources are regarded as equivalent KBs. We use the knowledge boundary module to determine the optimal source using self-regulatory mechanisms such as confidence calibration and reflective reasoning, and use the depth solving module to enhance the comprehensiveness of knowledge acquisition...

Key facts. Cited by 2 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 47 of its 50 references that are in the map. First posted on arXiv 21 Jun 2025.

Builds on

47 of 50 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization21 May
  2. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning25 Mar
  3. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  4. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  5. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models2 Oct
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  7. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 40

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  9. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  12. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
28 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  2. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  4. 2023Cognitive Architectures for Language Agentscited by 429
  5. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  6. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  7. 2023Improving Text Embeddings with Large Language Modelscited by 303
  8. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  9. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  10. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  11. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  12. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  13. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  14. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  15. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  16. 2020Thinking Fast and Slow in AIcited by 70
  17. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  18. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 63
  19. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTScited by 54
  20. 2023ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Modelscited by 44
  21. 2023ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferencescited by 43
  22. 2025Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RLcited by 36
  23. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  24. 2024MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexitycited by 29
  25. 2023MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answeringcited by 23
  26. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Lawcited by 19
  27. 2023Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQAcited by 17
  28. 2024To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answeringcited by 15

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedbackcited by 12
  2. 2025Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interactioncited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2025LAG: Logic-Augmented Generation from a Cartesian Perspective
  2. 2024Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
  3. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoning
  4. 2025RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
  5. 2024Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization
  6. 2025Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
  7. 2025ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs
  8. 2026ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs