AI RESEARCH
ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs
arXiv CS.CL
•
ArXi:2503.12918v2 Announce Type: replace Large language models (LLMs) have nstrated enhanced performance through the \textit{Thinking then Responding} paradigm, where models generate internal thoughts before final responses (aka, System 2 thinking). However, existing research lacks a systematic understanding of the mechanisms underlying how thinking patterns affect performance across model sizes. In this work, we conduct a comprehensive analysis of the impact of various thinking types on model performance and