paper-with-me

홈 › Papers

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

2026-01-11 · Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan arxiv

Reinforcement learning (RL) has catalyzed the emergence of Large Reasoning Models (LRMs) that have pushed reasoning capabilities to new heights. While their performance has garnered significant excitement, exploring the internal mechanisms driving these behaviors has become an equally critical research frontier. This paper provides a comprehensive survey of the mechanistic understanding of LRMs, organizing recent findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors. By synthesizing these insights, we aim to bridge the gap between black-box performance and mechanistic transparency. Finally, we discuss under-explored challenges to outline a roadmap for future mechanistic studies, including the need for applied interpretability, improved methodologies, and a unified theoretical framework.

📄 PDF Abstract BibTeX arXiv:2601.19928

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models

2026-01-02 · Liangming Pan, Jason Liang, Jiaran Ye, Minglai Yang 외 arxiv

Large Language Models (LLMs) have demonstrated remarkable abilities to solve problems requiring multiple reasoning steps, yet the internal mechanisms enabling such capabilities remain elusive. Unlike existing surveys tha…

How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning

2024-02-28 · Subhabrata Dutta, Joykirat Singh, Soumen Chakrabarti, Tanmoy Chakraborty

Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanisms of the models that facilitate CoT gen…

Answer Generation

Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models

2026-01-07 · Danchun Chen, Qiyao Yan, Liangming Pan arxiv

Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying taskspecific circuits, they leave open the questio…

Logical Reasoning

Select and Improve: Understanding the Mechanics of Post-Training for Reasoning

2026-06-11 · Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman arxiv

Reinforcement learning has rapidly emerged as a key component in the training of reasoning and coding models, yet it remains poorly understood from a mechanistic perspective. We study how and through what underlying proc…

Reinforcement Learning

Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs

2026-04-09 · Moein Salimi, Shaygan Adim, Danial Parnian, Nima Alighardashi 외 arxiv

Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an observation--has been relatively underexplored in Large Language Models…