The Universal Landscape of Human Reasoning

2025-10-24

AI Summary

Existing theories—such as classical logic and probabilistic models—struggle to unify and quantify the dynamic accumulation and transformation of information during human reasoning. To address this, we propose Information Flow Tracking (IF-Track), the first framework enabling quantitative, unified characterization of general human reasoning behavior. IF-Track employs large language models as probabilistic encoders to compute path-wise information entropy and information gain incrementally within a single metric space. Integrating fine-grained task analysis with cognitive modeling, it captures the full landscape of human reasoning. The framework reconciles single- and dual-process theories and reveals alignment mechanisms between AI and human cognition. Moreover, IF-Track identifies systematic reasoning biases, characterizes inter-individual variability, and elucidates how large language models reshape human reasoning trajectories—offering both theoretical insight and empirical utility for cognitive science and AI-augmented reasoning research.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Understanding how information is dynamically accumulated and transformed in human reasoning has long challenged cognitive psychology, philosophy, and artificial intelligence. Existing accounts, from classical logic to probabilistic models, illuminate aspects of output or individual modelling, but do not offer a unified, quantitative description of general human reasoning dynamics. To solve this, we introduce Information Flow Tracking (IF-Track), that uses large language models (LLMs) as probabilistic encoder to quantify information entropy and gain at each reasoning step. Through fine-grained analyses across diverse tasks, our method is the first successfully models the universal landscape of human reasoning behaviors within a single metric space. We show that IF-Track captures essential reasoning features, identifies systematic error patterns, and characterizes individual differences. Applied to discussion of advanced psychological theory, we first reconcile single- versus dual-process theories in IF-Track and discover the alignment of artificial and human cognition and how LLMs reshaping human reasoning process. This approach establishes a quantitative bridge between theory and measurement, offering mechanistic insights into the architecture of reasoning.

Problem

• Quantifying information entropy and gain during reasoning steps
• Unifying diverse human reasoning behaviors in single metric space
• Reconciling single versus dual-process theories through computational modeling

Innovation

• Information Flow Tracking quantifies reasoning entropy and gain
• LLMs serve as probabilistic encoders for step analysis
• Unified metric space models universal human reasoning behaviors