Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models

• URL: http://arxiv.org/abs/2601.00003v1
• Date: Fri, 28 Nov 2025 16:23:54 GMT
• Title: Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
• Authors: Shuqi Liu, Bowei He, Chen Ma, Linqi Song,
• Abstract summary: We introduce a reasoning-aware knowledge retrieval method that enriches large language models with information aligned to the logical structure of conversations.<n>We employ the Monte Carlo Tree Search-inspired search method to effectively navigate through knowledge sentences using common keywords.
• Score: 31.859833575765933
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) typically enhance their performance through either the retrieval of semantically similar information or the improvement of their reasoning capabilities. However, a significant challenge remains in effectively integrating both retrieval and reasoning strategies to optimize LLM performance. In this paper, we introduce a reasoning-aware knowledge retrieval method that enriches LLMs with information aligned to the logical structure of conversations, moving beyond surface-level semantic similarity. We follow a coarse-to-fine approach for knowledge retrieval. First, we identify a contextually relevant sub-region of the knowledge base, ensuring that all sentences within it are relevant to the context topic. Next, we refine our search within this sub-region to extract knowledge that is specifically relevant to the reasoning process. Throughout both phases, we employ the Monte Carlo Tree Search-inspired search method to effectively navigate through knowledge sentences using common keywords. Experiments on two multi-turn dialogue datasets demonstrate that our knowledge retrieval approach not only aligns more closely with the underlying reasoning in human conversations but also significantly enhances the diversity of the retrieved knowledge, resulting in more informative and creative responses.

Related papers

• Evolving Paradigms in Task-Based Search and Learning: A Comparative Analysis of Traditional Search Engine with LLM-Enhanced Conversational Search System [5.956874084659983]
  Large Language Models (LLMs) are rapidly reshaping information retrieval by enabling interactive, generative, and inference-driven search.<n>This study compares search behavior and learning outcomes in two environments: a standard search engine and an LLM-powered search system.
  arXiv  Detail & Related papers  (2025-11-29T04:14:14Z)
• Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation [81.18701211912779]
  We introduce an Adaptive Multi-Aspect Retrieval-augmented over KGs (Amar) framework.<n>This method retrieves knowledge including entities, relations, and subgraphs, and converts each piece of retrieved text into prompt embeddings.<n>Our method has achieved state-of-the-art performance on two common datasets.
  arXiv  Detail & Related papers  (2024-12-24T16:38:04Z)
• Knowledge Tagging System on Math Questions via LLMs with Flexible Demonstration Retriever [48.5585921817745]
  Large Language Models (LLMs) are used to automate the knowledge tagging task. We show the strong performance of zero- and few-shot results over math questions knowledge tagging tasks. By proposing a reinforcement learning-based demonstration retriever, we successfully exploit the great potential of different-sized LLMs.
  arXiv  Detail & Related papers  (2024-06-19T23:30:01Z)
• Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue [0.6650227510403052]
  We propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy. We also experiment with a large language model, ChatGPT, to take advantage of the improved retrieval performance.
  arXiv  Detail & Related papers  (2024-05-07T23:32:32Z)
• Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models [8.588056811772693]
  ConPARE-LAMA is a probe consisting of 34 million distinct prompts that facilitate comparison across minimal paraphrases. ConPARE-LAMA enables insights into the independent impact of either syntactical form or semantic information of paraphrases on the knowledge retrieval performance of PLMs.
  arXiv  Detail & Related papers  (2024-04-02T14:35:08Z)
• Generative Multi-Modal Knowledge Retrieval with Large Language Models [75.70313858231833]
  We propose an innovative end-to-end generative framework for multi-modal knowledge retrieval. Our framework takes advantage of the fact that large language models (LLMs) can effectively serve as virtual knowledge bases. We demonstrate significant improvements ranging from 3.0% to 14.6% across all evaluation metrics when compared to strong baselines.
  arXiv  Detail & Related papers  (2024-01-16T08:44:29Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Re-Reading Improves Reasoning in Large Language Models [87.46256176508376]
  We introduce a simple, yet general and effective prompting method, Re2, to enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs) Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. We evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.
  arXiv  Detail & Related papers  (2023-09-12T14:36:23Z)
• Synergistic Interplay between Search and Large Language Models for Information Retrieval [141.18083677333848]
  InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections. InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-12T11:58:15Z)
• Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters [52.725200145600624]
  We propose KnowExpert to bypass the retrieval process by injecting prior knowledge into the pre-trained language models with lightweight adapters. Experimental results show that KnowExpert performs comparably with the retrieval-based baselines.
  arXiv  Detail & Related papers  (2021-05-13T12:33:23Z)
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue [51.513276162736844]
  We propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge.
  arXiv  Detail & Related papers  (2020-02-18T11:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.