Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution
Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu
Abstract
The release of OpenAI’s O1 and subsequent projects like DeepSeek R1 has significantly advanced research on complex reasoning in LLMs. This paper systematically analyzes existing reasoning studies from the perspective of self-evolution, structured into three components: data evolution, model evolution, and self-evolution. Data evolution explores methods to generate higher-quality reasoning training data. Model evolution focuses on training strategies to boost reasoning capabilities. Self-evolution research autonomous system evolution via iterating cycles of data and model evolution. We further discuss the scaling law of self-evolution and analyze representative O1-like works through this lens. By summarizing advanced methods and outlining future directions, this paper aims to drive advancements in LLMs’ reasoning abilities.
BibTeX
@inproceedings{he-etal-2025-breaking,
title = "Breaking the Reasoning Barrier A Survey on {LLM} Complex Reasoning through the Lens of Self-Evolution",
author = "He, Tao and
Li, Hao and
Chen, Jingchang and
Liu, Runxuan and
Cao, Yixin and
Liao, Lizi and
Zheng, Zihao and
Chu, Zheng and
Liang, Jiafeng and
Liu, Ming and
Qin, Bing",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.386/",
doi = "10.18653/v1/2025.findings-acl.386",
pages = "7377--7417",
ISBN = "979-8-89176-256-5"
}