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

doi:10.24963/ijcai.2025/1195

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

Xiao-Wen Yang, Jie-Jing Shao, Lan-Zhe Guo, Bo-Wen Zhang, Zhi Zhou, Lin-Han Jia, Wang-Zhou Dai, Yu-Feng Li

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Survey Track. Pages 10770-10778.

https://doi.org/10.24963/ijcai.2025/1195

Keywords

Natural Language Processing: NLP: Language models
Machine Learning: ML: Neuro-symbolic methods

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 neuro-symbolic 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.

Xiao-Wen Yang, Jie-Jing Shao, Lan-Zhe Guo, Bo-Wen Zhang, Zhi Zhou, Lin-Han Jia, Wang-Zhou Dai, and Yu-Feng Li. 2025. Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10770–10778. https://doi.org/10.24963/ijcai.2025/1195

@inproceedings{ijcai2025p1195,
  title     = {Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models},
  author    = {Yang, Xiao-Wen and Shao, Jie-Jing and Guo, Lan-Zhe and Zhang, Bo-Wen and Zhou, Zhi and Jia, Lin-Han and Dai, Wang-Zhou and Li, Yu-Feng},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10770--10778},
  year      = {2025},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2025/1195},
  url       = {https://doi.org/10.24963/ijcai.2025/1195},
}

TY  - CPAPER
TI  - Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
AU  - Yang, Xiao-Wen
AU  - Shao, Jie-Jing
AU  - Guo, Lan-Zhe
AU  - Zhang, Bo-Wen
AU  - Zhou, Zhi
AU  - Jia, Lin-Han
AU  - Dai, Wang-Zhou
AU  - Li, Yu-Feng
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10770
EP  - 10778
DO  - 10.24963/ijcai.2025/1195
UR  - https://doi.org/10.24963/ijcai.2025/1195
ER  -