KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909666560180224 |
|---|---|
| author | Zhang, Dalong Xu, Jun Zhou, Jun Liang, Lei Yuan, Lin Zhong, Ling Sun, Mengshu Zhao, Peilong Wang, QiWei Wang, Xiaorui Du, Xinkai Hou, YangYang Ao, Yu Wang, ZhaoYang Gui, Zhengke Yi, ZhiYing Bo, Zhongpu Wang, Haofen Chen, Huajun |
| author_facet | Zhang, Dalong Xu, Jun Zhou, Jun Liang, Lei Yuan, Lin Zhong, Ling Sun, Mengshu Zhao, Peilong Wang, QiWei Wang, Xiaorui Du, Xinkai Hou, YangYang Ao, Yu Wang, ZhaoYang Gui, Zhengke Yi, ZhiYing Bo, Zhongpu Wang, Haofen Chen, Huajun |
| contents | 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 \textbf{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 \textbf{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 \textbf{knowledge boundary} module to determine the optimal source using self-regulatory mechanisms such as confidence calibration and reflective reasoning, and use the \textbf{depth solving} module to enhance the comprehensiveness of knowledge acquisition... |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17728 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation Zhang, Dalong Xu, Jun Zhou, Jun Liang, Lei Yuan, Lin Zhong, Ling Sun, Mengshu Zhao, Peilong Wang, QiWei Wang, Xiaorui Du, Xinkai Hou, YangYang Ao, Yu Wang, ZhaoYang Gui, Zhengke Yi, ZhiYing Bo, Zhongpu Wang, Haofen Chen, Huajun Computation and Language Artificial Intelligence 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 \textbf{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 \textbf{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 \textbf{knowledge boundary} module to determine the optimal source using self-regulatory mechanisms such as confidence calibration and reflective reasoning, and use the \textbf{depth solving} module to enhance the comprehensiveness of knowledge acquisition... |
| title | KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.17728 |