A Layered Intuition -- Method Model with Scope Extension for LLM Reasoning

2025-10-12

AI Summary

Large language models (LLMs) exhibit limited generalization to unseen indirect questions. Method: This paper proposes an Intuition–Method Hierarchical Reasoning Framework: the intuition layer enables rapid response, while the method layer decouples problem structure; it introduces, for the first time, a four-dimensional reasoning expansion mechanism—spanning vertical, horizontal, temporal, and spatial dimensions—to jointly construct knowledge trees and knowledge networks. We further define “method expansion entropy” as a novel metric quantifying reasoning diversity and independence. Contribution/Results: Experiments demonstrate that the framework significantly enhances LLM adaptability and reasoning breadth in complex, dynamic scenarios. Its effectiveness and scalability are validated across multiple open-ended tasks. The framework establishes a new paradigm for generalization modeling in LLMs, advancing structured, multi-dimensional reasoning beyond conventional sequential inference.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Existing studies have introduced method-based reasoning and scope extension as approaches to enhance Large Language Model (LLM) performance beyond direct matrix mappings. Building on these foundations, this paper summarizes and integrates these ideas into a unified Intuition-Method Layered Model with Scope Extension, designed to address indirected (unseen) issues more systematically. In this framework, intuition-based thinking provides rapid first-reaction answers, while method-based thinking decouples questions and solutions into transferable reasoning units. Scope extension is then applied to broaden applicability, including vertical (cause analysis), horizontal (parallel and generalized issues), and for the first time, temporal and spatial extensions, which expand reasoning across time and contextual dimensions. These extensions are organized into systematic knowledge trees that interconnect into a knowledge network, thereby increasing adaptability. To quantitatively evaluate this process, we propose the entropy of method extension, which measures the independence and diversity of extensions as an indicator of the system's capacity to solve unseen questions. By logically connecting existing approaches with new extensions and introducing an entropy-based evaluation framework, this work advances toward a more robust and extensible reasoning paradigm for LLMs in real-world problem-solving.

Problem

• Enhances LLM reasoning for unseen problems systematically
• Extends reasoning scope across temporal and spatial dimensions
• Quantitatively evaluates reasoning capacity using entropy metrics

Innovation

• Layered model with intuition and method reasoning
• Scope extension across temporal and spatial dimensions
• Entropy metric for evaluating method extension diversity