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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Xiao-Wen, Shao, Jie-Jing, Guo, Lan-Zhe, Zhang, Bo-Wen, Zhou, Zhi, Jia, Lin-Han, Dai, Wang-Zhou, Li, Yu-Feng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912544075022336
author Yang, Xiao-Wen
Shao, Jie-Jing
Guo, Lan-Zhe
Zhang, Bo-Wen
Zhou, Zhi
Jia, Lin-Han
Dai, Wang-Zhou
Li, Yu-Feng
author_facet Yang, Xiao-Wen
Shao, Jie-Jing
Guo, Lan-Zhe
Zhang, Bo-Wen
Zhou, Zhi
Jia, Lin-Han
Dai, Wang-Zhou
Li, Yu-Feng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13678
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
Yang, Xiao-Wen
Shao, Jie-Jing
Guo, Lan-Zhe
Zhang, Bo-Wen
Zhou, Zhi
Jia, Lin-Han
Dai, Wang-Zhou
Li, Yu-Feng
Artificial Intelligence
Machine Learning
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.
title Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.13678