From system 1 to system 2 : a survey of reasoning Large Language Models

Tools

Zhang, Duzhen and Li, Zhong-Zhi and Zhang, Ming-Liang and Zhang, Jiaxin and Liu, Zengyan and Yao, Yuxuan and Xu, Haotian and Zheng, Junhao and Chen, Xiuyi and Zhang, Yingying and Yin, Fei and Dong, Jiahua and Guo, Zhijiang and Song, Le and Liu, Cheng-Lin (2025) From system 1 to system 2 : a survey of reasoning Large Language Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. pp. 1-20. ISSN 0162-8828 (https://doi.org/10.1109/tpami.2025.3637037)

[thumbnail of Zhang-etal-2025-From-system-1-to-system-2]
Preview
 Text. Filename: Zhang-etal-2025-From-system-1-to-system-2.pdf
Accepted Author Manuscript
License: Creative Commons Attribution 4.0 logo
Download (4MB)| Preview

Abstract

Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human- like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning LLMs, trace the evolution of various reasoning models, and examine the core methods that enable advanced reasoning behind them. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time GitHub Repository to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field.

ORCID iDs

Zhang, Duzhen, Li, Zhong-Zhi, Zhang, Ming-Liang, Zhang, Jiaxin ORCID logoORCID: https://orcid.org/0000-0001-7355-7975, Liu, Zengyan, Yao, Yuxuan, Xu, Haotian, Zheng, Junhao, Chen, Xiuyi, Zhang, Yingying, Yin, Fei, Dong, Jiahua, Guo, Zhijiang, Song, Le and Liu, Cheng-Lin;
CORE (COnnecting REpositories)