Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models

2025-08-19

AI Summary

Insufficient reasoning capabilities in large language models (LLMs) hinder their progression toward artificial general intelligence (AGI). To address this, we propose a systematic enhancement pathway grounded in the neurosymbolic AI paradigm, organized along three synergistic mechanisms: Symbolic→LLM, LLM→Symbolic, and LLM+Symbolic. Our work establishes the first three-dimensional taxonomy—spanning methodology, challenges, and future directions—for neurosymbolic reasoning. We innovatively integrate neurosymbolic learning, formal task modeling, and LLM–symbolic engine co-architectures, yielding the most comprehensive survey of neurosymbolic reasoning techniques to date. Complementing this theoretical contribution, we open-source a GitHub platform that unifies benchmarks, toolkits, and reproducible case studies, thereby providing a unified framework and actionable guidelines for both fundamental research and practical deployment.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Large Language Models (LLMs) have shown promising results across various tasks, yet their reasoning capabilities remain a fundamental challenge. Developing AI systems with strong reasoning capabilities is regarded as a crucial milestone in the pursuit of Artificial General Intelligence (AGI) and has garnered considerable attention from both academia and industry. Various techniques have been explored to enhance the reasoning capabilities of LLMs, with neuro-symbolic approaches being a particularly promising way. This paper comprehensively reviews recent developments in neuro-symbolic approaches for enhancing LLM reasoning. We first present a formalization of reasoning tasks and give a brief introduction to the neurosymbolic learning paradigm. Then, we discuss neuro-symbolic methods for improving the reasoning capabilities of LLMs from three perspectives: Symbolic->LLM, LLM->Symbolic, and LLM+Symbolic. Finally, we discuss several key challenges and promising future directions. We have also released a GitHub repository including papers and resources related to this survey: https://github.com/LAMDASZ-ML/Awesome-LLM-Reasoning-with-NeSy.

Problem

• Improving reasoning abilities of large language models
• Addressing fundamental challenge in achieving artificial general intelligence
• Exploring neuro-symbolic approaches for enhanced LLM reasoning

Innovation

• Neuro-symbolic integration enhances LLM reasoning
• Three-way interaction between symbols and LLMs
• Formalized reasoning tasks with neurosymbolic paradigm