|国家预印本平台
首页|Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

来源:Arxiv_logoArxiv
英文摘要

Language has long been conceived as an essential tool for human reasoning. The breakthrough of Large Language Models (LLMs) has sparked significant research interest in leveraging these models to tackle complex reasoning tasks. Researchers have moved beyond simple autoregressive token generation by introducing the concept of "thought" -- a sequence of tokens representing intermediate steps in the reasoning process. This innovative paradigm enables LLMs' to mimic complex human reasoning processes, such as tree search and reflective thinking. Recently, an emerging trend of learning to reason has applied reinforcement learning (RL) to train LLMs to master reasoning processes. This approach enables the automatic generation of high-quality reasoning trajectories through trial-and-error search algorithms, significantly expanding LLMs' reasoning capacity by providing substantially more training data. Furthermore, recent studies demonstrate that encouraging LLMs to "think" with more tokens during test-time inference can further significantly boost reasoning accuracy. Therefore, the train-time and test-time scaling combined to show a new research frontier -- a path toward Large Reasoning Model. The introduction of OpenAI's o1 series marks a significant milestone in this research direction. In this survey, we present a comprehensive review of recent progress in LLM reasoning. We begin by introducing the foundational background of LLMs and then explore the key technical components driving the development of large reasoning models, with a focus on automated data construction, learning-to-reason techniques, and test-time scaling. We also analyze popular open-source projects at building large reasoning models, and conclude with open challenges and future research directions.

Zefang Zong、Jingwei Wang、Yu Li、Jie Feng、Chen Gao、Yiwen Song、Sijian Ren、Jiahui Gong、Tianjian Ouyang、Jingyi Wang、Fanjin Meng、Chenyang Shao、Qianyue Hao、Yunke Zhang、Qinglong Yang、Yuwei Yan、Xiaochong Lan、Xinyuan Hu、Yong Li、Fengli Xu

计算技术、计算机技术

Zefang Zong,Jingwei Wang,Yu Li,Jie Feng,Chen Gao,Yiwen Song,Sijian Ren,Jiahui Gong,Tianjian Ouyang,Jingyi Wang,Fanjin Meng,Chenyang Shao,Qianyue Hao,Yunke Zhang,Qinglong Yang,Yuwei Yan,Xiaochong Lan,Xinyuan Hu,Yong Li,Fengli Xu.Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models[EB/OL].(2025-01-16)[2025-08-02].https://arxiv.org/abs/2501.09686.点此复制

评论