Auto-Relational Reasoning

2026-04-29

AI Summary

Current large language models exhibit limited performance on structured logical reasoning tasks, such as intelligence tests. This work proposes a novel hybrid intelligence framework that, for the first time, deeply integrates an object–relation formal reasoning mechanism with neural networks to enable general-purpose symbolic reasoning without requiring prior knowledge. The approach efficiently solves problems in zero-shot or few-shot settings and achieves 98.03% accuracy on standard intelligence tests—equivalent to the top 1% of human performance (IQ 132–144)—significantly outperforming existing purely neural or purely symbolic methods. These results demonstrate the substantial potential of neuro-symbolic collaborative architectures for complex reasoning tasks.

Abstract

Background & Objectives: In the last decade, Machine learning research has grown rapidly, but large models are reaching their soft limits demonstrating diminishing returns and still lack solid reasoning abilities. These limits could be surpassed through synergistic combination of Machine Learning scalability and rigid reasoning. Methods: In this work, we propose a theoretical framework for reasoning through object-relations in an automated manner integrated with Artificial Neural Networks. We present a formal analysis of the Reasoning, and we show the theory in practice through a paradigm integrating Reasoning and Machine Learning. Results: This paradigm is a system that solves Intelligence Quotient problems without any prior knowledge of the problem. Our system achieves 98.03% solving rate corresponding to the top 1% percentile or 132-144 iq score. This result is only limited by the small size of the model and the processing capabilities of the machine it run on. Conclusions: With the integration of prior knowledge in the system and the expansion of the dataset, the system can be generalized to solve a large category of problems. The functionality of the system inherently favors the solution of such problems in few-shot or zero-shot attempts.

Problem

• reasoning
• machine learning
• intelligence quotient
• neural networks
• zero-shot learning

Innovation

• Auto-Relational Reasoning
• Neural-Symbolic Integration
• Zero-Shot Reasoning
• Object-Relation Modeling
• IQ Problem Solving