logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

(How) Do reasoning models reason?

delete2025-04-12
delete0
PRE
AI
S
Subbarao Kambhampati *
K
Kaya Stechly
K
Karthik Valmeekam
DOI：10.1111/nyas.15339delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
We provide a broad unifying perspective on the recent breed of large reasoning models such as OpenAI o1 and DeepSeek R1, including their promise, sources of power, misconceptions, and limitations.
Keywords:
large language models
reasoning
planning
reinforcement learning post-training
test-time inference

Journal

Annals of the New York Academy of Sciences cover
Annals of the New York Academy of Sciences
IF:
4.8
Papers:
2.5K
Citations:
4.4W

Organization

No organization information available